text
stringlengths
28
334k
<s>[INST] So there's this uh so there's this attention mechanism that somehow self referential, that's fundamental to what consciousness is. So, just uh ask you a question, I don't know how much you're familiar with the recent breakthroughs, the natural language processing, They use attentional mechanism. Use something called transformers two uh learn patterns and sentences by allowing them, I work to focus its attention to particular parts of the sentence at each individual? So like Perma tries and make it learn about all the dynamics of a sentence by having like a little window into the into the sentence. Do you think that's like a little step towards that Eventually we will take us to the intentional mechanisms from which consciousness can emerge. [/INST] Not quite, I think it models only one aspect of attention. In the early days of automated language translation, there was a example that I found particularly funny where somebody tried to translate a text from english into german and it was a bad broke the window and the translation in german was fledermaus. It's a practice fenster mit einem baseball schlager, so to translate back into bed uh this flying mammal broke the window with a baseball bat and uh it seemed to be the most similar to this program because it somehow maximized uh the possibility of translating the concept that into german in the same sentence. And there's some mistake that the transformer model is not doing because it's tracking identity and the attentional mechanism. And the transformer model is basically putting its finger on individual concepts and make sure that these concepts um pop up later in the text and tracks basically the individuals through the text and that's why uh the system can learn things that other systems couldn't before it which makes it for instance possible to write a text where it talks about the scientist and the scientists as a name and as a pronoun and it gets a consistent story about that thing. What it does not do, it doesn't fully integrate this. So it is meaning falls apart. At some point it loses track of this context, It does not yet understand that everything that it says has to refer to the same universe and this is where this thing falls apart. But the attention in the transformer model does not go beyond tracking identity. And tracking identity is an important part of attention, but it's a different, very specific attentional mechanism. Um it's not the one that gives rise to the type of consciousness that we have </s><s>[INST] just to linger and what do you mean by identity in the context of language? [/INST] So when you talk about language, we have different words that can refer to the same concept and in the sense concepts? Yes. And it can also be in a nominal sense or in Mexico sense that you say. Uh this word does not only refer to this class of objects, but it refers to a definite object to some kind of agent that weaves their way through the story and it's only referred by different ways in the language. So, the language is basically a projection from a conceptual representation from a scene that is evolving into discrete string of symbols and what the transformer is able to, it learns um aspects of this projection mechanism that other models couldn't learn. </s><s>[INST] So, have you ever seen an artificial intelligence or any kind of construction idea that allows for unlike neural networks or perhaps within neural networks that's able to form something where the space of concepts continues to be integrated. So what you're describing, building a knowledge base, building this consistent larger and larger sets of ideas that would then allow for a deeper understanding [/INST] Wittgenstein thought that we can build everything from language from basically a logical grammatical construct. And I think to some degree that was also what Minsky believed. So that's why we focus so much on common sense reasoning and so on and um project that was inspired by him with psych. Um that was basically yes of course uh ideas don't die, only people die </s><s>[INST] and that's true but [/INST] and outside is a productive project. It's just probably not one that is going to converge to general intelligence. The thing that Wittgenstein couldn't solve and he looked at this in his book at the end of his life, philosophical investigations was the notion of images, so images play an important role in track titles. The tractor does an attempt to basically two and philosophy ontological probing language to design a logical language in which you can do actual philosophy that rich enough for doing this. And the difficulty was to deal with perceptual content and eventually I think he decided that he was not able to solve it and I think that's preempted the failure of the largest program in Ai and the solution as we see it today is we need more general function approximation. There are functions, geometric functions that we learnt to approximate that cannot be efficiently expressed and computed in a governmental language. We can of course build automata that go via number theory and so on to learn in algebra and then compute an approximation of this geometry. But to create language and geometry is not an efficient way to think about it. </s><s>[INST] So functional where you kind of just said that you know, networks are sort of the approach and you don't know what it takes is actually more general than uh then what can be expressed through language. [/INST] So what can be efficiently expressed through language at the data rates at which we process grammatical language? </s><s>[INST] Okay, so you don't think so, you don't think languages. So you disagree with Wittgenstein, that language is not fundamental to [/INST] agree with Wittgenstein. Just agree with the late Wittgenstein and uh I also agree with the beauty of the early Wittgenstein. I think that the track titles itself is probably the most beautiful philosophy text that was written in the 20th century, </s>
<s>[INST] I still wonder what kind of applications are yet to be enabled by it. Because so much the interesting thing about N. F. T. S. You know, if you look outside of art is uh just like money, you can start playing with different social constructs is you can start playing with the ideas, you can start playing with with uh even like investing, somebody was talking about almost creating an economy out of uh like creative people or influencers like if you start a Youtube channel or something like that, you can invest in that person and you can start trading their creations and then almost like create a market out of people's ideas, out of people's creations, out of the people themselves that generate those creations. And there's a lot of interesting possibilities of what you can do with that. I mean, it seems ridiculous, but you're basically creating hierarchy of value, maybe artificial in the digital world and they're trading that but in so doing are inspiring people to create. So maybe uh as sort of our economy gets better and better and better where actual work in the physical space becomes less and less in terms of its importance maybe will completely be operating in the digital space where uh where these kinds of economies have more and more power and then you have to have this kind of block chains. Two, the scalability, security and decentralization, decentralization is of course the tricky one because uh people in power start to get nervous [/INST] absolutely once in power, you always never be supplanted by somebody else. But this is your job seeing relations, you don't have a job, a tough job and now everybody wants it. </s><s>[INST] Well, what is your sense about our our time and the future? Hope about the decentralization of power. Do you think that's something that we can actually achieve, given that power corrupts and absolute power corrupts? Absolutely. And it's so wonderful to be absolutely powerful. [/INST] Well, good question. So, so first of all, I believe that by the way that he is a is a complex questions or legs uh like all the rest of your questions. </s><s>[INST] Uh very sorry, [/INST] it's okay. I'm enjoying it. So, but So there are two things. First of all, power has been centralized provider reasons when you want to get it is easier for somebody, even a single person to grab power. But there is also some kind of a technology lack very off but justified having empower because in a way in a society in which even communication never mind Blockchain which is common knowledge, but even simple unilateral communication is hard. It's much easier to say you do as I say because the alternative but as so there is a little bit of a technology barrier. But I think that and and now to get to this is a common knowledge and it is a totally different story. Now we have finally the technology for doing this. So that is one part. But I really believe that not by having a distributed system, not only you don't have a you have to actually much more stable and durable system because not only for corruption, but even for things that go Australia. And given it long enough time by strange version of Murphy's law, whatever goes wrong goes wrong. And so and if the power is diffused, you actually are much more stable if you look at any any living uh complex living being is distributed. I mean I don't have somebody is a okay, tell Sylvia now it's time to eat. Uh you </s><s>[INST] have millions of cells in your body, you have billions of bacteria. [/INST] Exactly help me in the guts. I think, you know, we are in a super and somehow keeps us alive. It is uh, so it's strange enough, however, when we design systems, we designed them centralist, we ourselves are distributed beings. And when we plan to say, okay, I want to get an architecture. How about I make a pyramid? I put west on the top and the power flows down. And so again, it's a little bit perhaps of a technology problem. But now the technology is there. So that is a big challenge to rethink. We want to organize the power in very large system and and and and distributed system in my opinion are much more resilient. Let's put the best way. There was a mine of my uh italian compatriots. All right. You know Machiavelli who who looked at the time, there was a big, there was a bunch of a small state democratic republic of Florence of veganism and the other thing and there was the Ottoman empire, but at the time was an empire and assad and was very centralized and aim at the political observation that goes roughly to say whenever you have such a central. I think it's very hard to overtake, but the former government is centralist. But if you get it, it's so easy to keep population one instead with africa with other things are much more uh resilient time when the power is distributed is much more is going to be lasting for much longer time. </s><s>[INST] And ultimately, maybe the human spirit wants that kind of resilience wants that kind of distribute. It's just that we didn't have technology throughout history. Machiavelli didn't have the computer and the internet and uh, [/INST] that is certainly part of the reason. Yes, </s><s>[INST] you've written an interesting blog post. If we take a step out of the realm [/INST] of bits </s><s>[INST] and into the realm of governance, you wrote a blog post about making al gore and governance decentralized. Uh, can you explain what that means? The philosophy behind that? You know, how you decentralize basically all aspects of this kind of system. [/INST] Well, the philosophy and how let's start with a philosophy. So I really believe that uh, nothing fixed last very long. And so I really believe that life is about intelligent adaptation, things change. And we have to be nimble and adjust to change. And uh, when I, when I see a lot of uh, they kept the project actually very proud to say is fixed in stone and right, you know, called this law is called ivory for the code that will never change you go, wow, what I'm saying? This is a recipe to me of disaster. Not immediately, but soon. Just imagine you take a notional liner and you want to go, I don't know from Lisbon to new york and you set the course iceberg, no iceberg Tempesta, no Tempest and all. It doesn't matter. But it's not the way you need a till you need to correct, you need to adjust and um, and so um, by the way we design, I'll go around with the idea that uh, the code was evolving as the needs And of course however, is a system in which and every time there is an adjustment, you must have essentially a vote with uh right now is uh orchestrated that 90% of the steak and I say, OK, we are ready, we agree on the next version and we pick up this version. So we are able to evolve without losing too many components left and right. But I think without evolving any system essentially become athletic and that is going to shrivel and die sooner or later. And, and so that is um, is needed. And what do you want to do under the Blockchain? You have a perfect platform in which you can log your wish is your votes, your things so that you have a guarantee that whatever vote you express is actually seen by everybody else. So everybody sees really the outcome. Call it of a referendum of a change and better is uh, in my opinion or a system that wants to live long as to adapt. </s>
<s>[INST] That's a cool thing for a doctor to say. I mean, depends how badass they saw when they said So that's a tough conversation judo one. What's, what's this with your wife? What's that relationship like? So you're both a little crazy a little bit in the in the good sense or from my perspective, in a good sense. [/INST] Yeah, it's just we've, we understand that when it, when you set a goal to do something, you're not signing on for the good, you're signing on for the bad and I don't think a lot of people understand that. </s><s>[INST] That's like a valentine's day card from Travis stevens, [/INST] you have to like accept everything negative that could possibly happen. And until you do, you're never gonna make it because you always sell yourself short, you'll never go far enough. </s><s>[INST] And if you sign up for the whole thing, then the negative is just like, oh great. I expected that if you're experiencing the negative, they're also experienced the negative and if you overcome it, maybe they'll get knocked out from [/INST] maybe they won't deal with it. Maybe they won't train through it Right when I had my five herniated disc and I was in a neck brace, I was still in the gym at seven am doing whatever it is I could do because my job is to be at the gym, </s><s>[INST] David Goggins. I don't know if you know the guy, he's gone, he's damaged a lots of parts of his body. Like you trying to achieve things. So unlike you, his achievements are like your achievements come with the metal. He's just running in the darkness in the middle of nowhere, by himself. It's like, I mean, it's the same probably is with you if you're able to be introspective about it is he's just battling his own inner demons and working through those and he's breaking up, breaking his body doing so are you cognizant of the trade off of the fact that, you know, you're damaging your body to get to these levels of achievements of this level of excellence, of this level of greatness. [/INST] I mean, I guess that depends on what you consider damage really, because I don't really see that I have damaged my body. If anything, I think I've strengthened it. My body can go through more than your scan whose is weaker, right? It's just like it's just like the thai boxers right in order to strengthen their shins. They gotta break it a few times. Yeah, it's just nature of the </s><s>[INST] beast. You just had to break a bunch of stuff to find where the weak points are and then made them stronger [/INST] or strengthen the areas around it to strengthen it by, you know, share relation to it. </s><s>[INST] But the problem is like you may not be able to do judo Like four until you're 70. [/INST] Why not? I may not be able to judo to the level I used to don't get me wrong, but I can still do judo because I think a lot of people struggle with, they want to keep doing it like they used to be able to do it. I don't try to do judo like I used to like you're seeing here, I'm not that guy anymore. I accept that I don't even try to be that guy anymore. I'm a completely different player today than I am when I was winning olympic medals. And so I guess when you're looking at like my journey and the trade off is I never sacrificed anything. The people around me sacrificed for me and I never had a downturn after the olympics because I never identified as an Olympian. </s><s>[INST] You know, a lot of olympians suffer from depression because [/INST] they identify as it now they don't have who they are. </s><s>[INST] Where was your personal moment of greatness? Like or do you not experience life that way where you were truly proud to be yourself? Like every day I wake up your [/INST] uh you wake up and you're not proud of who you are then, do you've really got to seek out some like help. </s><s>[INST] So that's first of all, Okay, I'll do that because I definitely not proud of who I am. I just wonder if you didn't identify with the olympics. Was there times maybe in the training room maybe in Japan? Like what you're, you just kind of felt like [/INST] I get more of an emotional yes trigger right where like I feel proud of what I've done when I've set to a task and I've done it. </s><s>[INST] So I'm just saying you task [/INST] and the more challenging the task, the more reward. </s><s>[INST] You fought a lot of amazing battles in 2016 Olympics. So you got, You beat the, let's see the world number four in the quarter finals. It's like a replay every single olympics. Your [/INST] all the people, I got terrible draw </s><s>[INST] saying terrible draws and then you're facing this is where I was like watching this. I'm like he screwed you face the world number one Georgian and [/INST] by the way for people who don't know, he beat me five times to my beating him once and the one time I beat him was in London and all other times he beat me, he beat me by poem and not by like a little throw like he threw me on my head at one point we were in Georgia. I'm fighting him in the final. I go to my teammate and I go guess what? Make sure you watch this fight? Somebody's getting thrown free pone dispatching and this is a magical distance and about a minute in I tried to take his head off with a big koshi group which is like a head and arm. He caught me and then threw me on my head and end of the match. Okay. </s>
<s>[INST] when I was like eight year old. Yeah, I mean, there is, and you do, there's folks at OpenAI, including yourself, that do see the importance of these issues to discuss about them under the big banner of AI safety. That's something that's not often talked about with the release of GPT-4. How much went into the safety concerns? How long also you spent on the safety concern? Can you, can you go through some of that process? Yeah, sure. [/INST] What went into AI safety considerations of GPT-4 release? So we finished last summer. We immediately started giving it to people to Red Team. We started doing a bunch of our own internal safety emails on it. We started trying to work on different ways to align it. And that combination of an internal and external effort, plus building a whole bunch of new ways to align the model. And we didn't get it perfect by far, but one thing that I care about is that our degree of alignment increases faster than our rate of capability progress. And that I think will become more and more important over time. And I don't know, I think we made reasonable progress there to a more aligned system than we've ever had before. I think this is the most capable and most aligned model that we've put out. We were able to do a lot of testing on it and that takes a while. And I totally get why people were like, give us GPT-4 right away. </s><s>[INST] But I'm happy we did it this way. Is there some wisdom, some insights about that process that you learned? Like how to solve that problem that you can speak to? [/INST] How to solve the alignment problem? So I want to be very clear. I do not think we have yet discovered a way to align a super powerful system. We have something that works for our current scale called RLHF. And we can talk a lot about the benefits of that and the utility it provides. It's not just an alignment. Maybe it's not even mostly an alignment capability. It helps make a better system, a more usable system. And this is actually something that I don't think people outside the field understand enough. It's easy to talk about alignment and capability as orthogonal vectors. They're very close. Better alignment techniques lead to better capabilities and vice versa. There's cases that are different and they're important cases. But on the whole, I think things that you could say like RLHF or interpretability that sound like alignment issues also help you make much more capable models. And the division is just much fuzzier than people think. And so in some sense, the work we do to make GPD4 safer and more aligned looks very similar to all the other work we do of solving the research and engineering problems </s><s>[INST] associated with creating useful and powerful models. So RLHF is the process that came up applied very broadly across the entire system. More human basically votes. What's a better way to say something? What's, you know, if a person asks, do I look fat in this dress? There's different ways to answer that question [/INST] that's aligned with human civilization. And there's no one set of human values or there's no one set of right answers to human civilization. So I think what's gonna have to happen is we will need to agree on as a society on very broad bounds. We'll only be able to agree on a very broad bounds of what these systems can do. And then within those, maybe different countries have different RLHF tunes. Certainly individual users have very different preferences. We launched this thing with GPD4 called the system message, which is not RLHF, but is a way to let users have a good degree of steerability over what they want. </s><s>[INST] And I think things like that will be important. Can you describe system message and in general, how you were able to make GPD4 more steerable based on the interaction that the user can have with it, [/INST] which is one of those big, really powerful things. So the system message is a way to say, you know, hey model, please pretend like you, or please only answer this message as if you were Shakespeare doing thing X, or please only respond with Jason no matter what was one of the examples from our blog post. But you could also say any number of other things to that. And then we tune GPD4 in a way to really treat the system message with a lot of authority. I'm sure there's jail, they're always, not always hopefully, but for a long time, there'll be more jail breaks and we'll keep sort of learning about those. But we program, we develop whatever you wanna call it, the model in such a way to learn </s><s>[INST] that it's supposed to really use that system message. Can you speak to kind of the process of writing and designing a great prompt as you steer GPD4? [/INST] I'm not good at this. I've met people who are. Yeah. And the creativity, the kind of, they almost, some of them almost treat it like debugging software. But also they, I've met people who spend like, you know, 12 hours a day for a month on end on this, and they really get a feel for the model and a feel how different parts of a prompt </s><s>[INST] compose with each other. Like literally the ordering of words, this, [/INST] the choice of words. Yeah, where you put the clause, </s>
<s>[INST] yeah, slide [/INST] it, slide it </s><s>[INST] across to buy the book and just leave it, leave it, give it to everybody on your team. Okay, So we solved the ball because he's my problem with this. Is there a case to be made that even for like communication between you and I, we should move away from from email. For example. There's a guy ever recently, I don't know if you know comedians, but there's a guy named Joey Diaz that I've had an interaction with recently and that guy, first of all, the sweetest human, despite what his comedy sounds like. He's the sweetest human being and he's a big proponent of just pick up the phone and call and it makes me so uncomfortable people call me, it's like, I don't know what to do with this thing. Uh but it kind of gets everything done quicker. I think if I remove the anxiety from that, is there a case to be made for that or his email could still be the most efficient way to do [/INST] this. No. Look, if you if you have to interact with someone, there's a lot of efficiency in synchrony, right? And there's something from distributed system theory where, you know, if you go from synchronous to asynchronous networks, there's a huge amount of overhead to the asynchronous. So actually the protocols required to solve things in a synchronous networks are significantly more complicated and fragile. The synchronous protocol. So if we can just do real time it's usually better. And also from uh interaction like social connection standpoint, there's a lot more information in the human voice, in the back and forth. Uh Yeah, if you just call some very generational right? Like our generation will be comfortable talking on the phone in a way that like a younger generation isn't but an older generation is more comfortable with, well you just call people whereas we so there's a happy medium. But most of my good friends, we just talk we have regular phone calls. Yeah, it's not, I don't just call them, we schedule, we schedule it just on text like yeah, you want to talk sometime soon. </s><s>[INST] Do you do you ever have a process that around friends? [/INST] Not really. </s><s>[INST] I feel like I should, I feel like [/INST] when you have like a lot of interesting friend possibilities as you have. Like an interesting problem, Right? Like really interesting people you can talk </s><s>[INST] to. Well that's, that's one problem. The other one is the introversion where I'm just afraid of, people get really stressed, like I freak out. And so [/INST] you picked a good line of </s><s>[INST] work? Yeah, Now perhaps it's the Goggins thing, it's like facing your fears or whatever. Uh, but it's almost like there's uh, it has to do with the timetables thing and the deep work that the nice thing about the processes is it not only automates sort of uh automates away the contact switching, it ensures you do the important things to like it's like prioritized, the thing is with email because everything is done over email. You can be lazy in the same way with like social networks and and do the easy things first that are not that important. So the process also enforces that you do the important things. And for me, the important things is like it sounds weird, but like social [/INST] connection, that's one of the most important things in all of human existence. And doing it. The paradoxical thing, I got into this for digital minimalism. Uh, the more you sacrifice on behalf of the connection, the stronger the connection feels right? So sacrificing nontrivial time and attention on behalf of someone is what tells your brain that this is a serious relationship, which is why social media had this paradoxical effect making people feel less social because it took two friction out of it. And so the brain just doesn't like, yeah, you've been commenting on this person's whatever you've been retweeting them or sending them some text, you haven't, it's not hard enough. And then then the perceived strength of that social connection diminishes where if you talk to them or go spend time with them or whatever, you're going to feel better about it. So the friction is good. I have a thing with some of my friends where at the end of each call, we take a couple days to schedule the next, then, you know, it's like I do with haircuts or something, right? Like if I don't schedule it, then I'm never gonna get my haircut right. And so it's like, okay, when you want to talk next, you know? </s><s>[INST] Yeah, that's a, that's a really good idea. I I just don't call friends and uh like every 10 years I do something dramatic for them so that we maintain the French, like I'd murder somebody that they really don't like. [/INST] I just think Joey might ask </s><s>[INST] you. Yeah, that's right. Well, that's one of my favorite lex, you gotta come out [/INST] of New Jersey. </s><s>[INST] That's exactly, we're [/INST] going to do that robot dog of yours, we're </s><s>[INST] going to go down to Jersey. There's especially human, I love the comedian world, they've been shaking up, I don't know if you listen to joe Rogan, all those folks, they kind of uh are doing something interesting form it and, and academia there shaking up this world a little bit like podcasting because comedians are paving the way for podcasting. And so you have like Andrew Huberman who's a neuroscientist at stanford in front of mind now, he's like into podcasting now and you're into podcast. Of course, you're not necessarily podcast about computer science currently, right? But that it feels like you could have a lot of the free spirit of the comedians implemented by the people who are academically [/INST] trained to actually have a nice specialty. </s>
<s>[INST] So in general, any applications to cast a gradient descent and neural networks is is amazing to you. So that or is there a particular application in natural language reinforcement learning? Ah and also what do you attribute that success to? Is it just scale what profound insight can we take from the fact that the thing works for gigantic uh sets of variables. [/INST] I mean the interesting thing is these algorithms, they were invented uh decades ago and people actually gave up on the idea and you know, back then they thought that we need profoundly different algorithms and they spent a lot of cycles on very different algorithms. And I believe that, you know, we have seen that various various innovations that say like transformer or drop out or so they can uh you know pass the help. But it's also remarkable to me that this algorithm from sixties or so. I mean you can even say that the great in dissent was invented by life needs in I guess 18th century or so, that actually is the court of learning in the past. People are it's almost like a out of the maybe an ego. People are saying that it cannot be the case that such a simple algorithm is there, you know, uh huh could solve complicated problems. So they were in search for the other algorithms and as I'm saying like I believe that actually we are in the game where there is there actually frankly three levels, there is compute there are algorithms and there is data and if you want to build intelligence systems, we have to pull all three levels and they are actually multiplication. And it's also interesting. So you ask, is it only compute uh people internally, they did the studies to determine how much gains they were coming from different levers. And so far we have seen that more gains came from computer algorithms, but also we are in the world that in case of compute there is a kind of, you know, exponential increase in funding And at some point it's impossible to uh investment. It's impossible to, you know, invest $10 trillion. We are speaking about their let's say all taxes in us. Uh </s><s>[INST] but you're talking about money that could be innovation in the compute [/INST] that's true as well. So, I mean they're like a few pieces, the one pieces. Human brain is an incredible supercomputer and they're like a it has 100 trillion parameters. Or like if you try to count various quantities in the brain there like a neuron synapses are a small number of neurons, there is a lot of synapses. It's unclear even how to map synapses to uh parameters of neural networks, but it's clear that there are many more. Uh so it might be the case that our networks are still somewhat small. Uh It also might be the case that they are more efficient than brain or less efficient by some by some huge factor. Uh I also believe that there will be like you know, at the moment we are at the stage that this neural networks they require 1000 X. Or like a huge factor of more data than humans do. And it will be a matter of uh um there will be algorithms that vastly decreased sample complexity, I believe so. But the place where we are heading today is their domains which contains million x more data. And even though computers might be 1000 times slower than humans in learning, that's not the problem. Okay. For instance, uh I believe that it should be possible to create superhuman therapists. Bye. And And they're like even simple steps of of of doing what of of doing it. And you know, the core reason is there is just machine will be able to read way more transcripts of therapies and then it should be able to speak similar Tennessee with many more people and it should be possible to optimize it all in parallel and well </s><s>[INST] there's now you're touching on something I deeply care about and think is way harder than we imagine. Um What's the goal of the therapist? [/INST] What's the goal of therapist? </s><s>[INST] Mm So okay so one goal now this is terrifying to me. But there's a lot of people that contemplates suicide suffer from depression ah And they could significantly helped with therapy and the idea that ai algorithm might be in charge of that. It's like a life and death task. It's a the stakes are high. So one goal for a therapist whether human or ai is to prevent suicide ideation to prevent suicide. How do you achieve that? [/INST] So let's see. So to be clear I don't think that the current models are good enough for such a task because it requires insane amount of understanding empathy. And the models are far from this place. </s><s>[INST] But it's but do you think that understanding empathy that signal is in the data? [/INST] I think there is some signal in the data. Yes I mean there are plenty of transcripts of conversations and it is possible to it is possible from it to understand personalities. It is possible from it to understand if conversation is uh friendly uh amicable uh antagonistic. It is I believe that the you know given the fact that the models that we train now they can they can have their chameleons that they can have any personality, They might turn out to be better in understanding personality of other people than anyone else. And the actual pathetic to be empathetic, </s>
<s>[INST] can you elaborate innocuous, get him out of the book. Uh [/INST] basically I I set up pretty defensively as white. I wasn't really crossing into his half at the start at all. I was just, I played more like a system more than like a concrete opening. It was like I'm going to set up my pieces this way you can set them up however you want and then later where sort of the armies are going to meet. I'm not gonna try and bother you at the start and </s><s>[INST] that means you can have with as many pieces as possible kind of pure chest in the middle game without any of the lines, the standard lines in the opening. [/INST] And so there was at some point a couple of exchanges, then some maneuvering a little bit better. Then he was sort of equalizing and then I started to take too many risks and I was still sort of fine. Um, but then at some point I realized that I've gone a bit too far and I had to be really careful. Now I just </s><s>[INST] froze, I [/INST] just completely froze uh </s><s>[INST] mentally, like [/INST] mentally </s><s>[INST] I [/INST] realized that I mean all the thoughts of </s><s>[INST] I [/INST] might lose this, what have I done? Why did I take so many risks? I knew that I could have drawn at any moment. Just be patient. Don't give him these opportunities. What </s><s>[INST] triggered that like face transition in your mind? [/INST] No, it was one </s><s>[INST] thing a [/INST] position on the board like realizing like there was one particular move he played that I missed and then like, and then I, I realized this could potentially not go my way. So then I made another couple of mistakes and he to his credit, like once he realized he had a chance, he was like, he knew that this was his one chance he had to take it. And so he did. And yeah, that's that's the worst I've ever felt after um after a chess game, I realized that I'm probably gonna lose my title against somebody who's not even close to my level and I've done it because of my own stupidity most of all. Uh and that was really, really um at the time, like I was all in my own head, that was, that was hard to deal with and I felt like I didn't really recover too much for the next game. So what I did, there was a free day after the eighth game, so I did something that I never did at any other world championship, like I after game eight, I just, I got drunk with my team and </s><s>[INST] a standard procedure. [/INST] No, no, that's that's the only time that's happening in the world championship during the match. So yeah, just try to forget. But still before game nine, game nine, I was a little bit more relaxed, but I was still a bit nervous then Game nine, I was almost lost as well. And then only game 10, Game 10, I was still, I wasn't in a great mood, I was really, really tense. Um the opening was good, </s><s>[INST] I [/INST] had some advantage, I was getting optimistic, then I made one mistake, he could have forced to draw and then the old old, the negativity came back. Like I was thinking during game like how I'm going to play for a win with black in the next game? Like what, what, what am I doing? And then, you know, eventually it ended. It ended well, didn't find the right line. I ground him down actually. I played at some point pretty well in the end game. And um after that game, like there was such a weight lifted. No, I after that there was like no thought of losing the match whatsoever. I knew that okay. I had basically gotten away with um not with murder but gotten away with something. </s><s>[INST] What can you say about the after game mate? Where are the places you've gone in your mind? Do you go to some dark places? We're talking about like depression. Do you think about quitting at that point? [/INST] No, I mean I think about quitting every time I lose the classical or at least I used to like, especially if it's in a stupid way, I'm thinking like, okay, if I'm gonna gonna play like this, if I'm going to do things that I know are wrong, then you know, I might as well quit. No, that's happened, that's happened a bunch of bunch of times and I've definitely gotten a bit more carefree about losing these days, which it's not necessarily a good thing, like my hatred of losing led to me not losing a lot. And it also lit the fire under me that I think my performance after losses in, In classical chess over the last 10 years, it's like over 2900. Like I really play well after a loss even though it's really, really unpleasant. So apparently </s><s>[INST] like, [/INST] I don't think the way that I dealt with them is particularly healthy, but it's worked, </s><s>[INST] it's worked so far. But then you've discovered now love for winning to where ultimately longevity wise creates more [/INST] fun. </s><s>[INST] What's the perfect day in the life of magnus carlsen on a day of big chess match, It doesn't have to be world championship, but if it's, if it's a chess match you care about what, what time do you wake up, what do you eat? [/INST] It depends on when the game is, but let's say the game is at three. I'll probably wake up pretty late at about 11, then I'll go for go for a walk. Might listen to some podcasts. Maybe I'll spend a little bit of time looking at some, you know, some NBA game from last night or whatever to </s><s>[INST] not just related stuff. [/INST] No, no, no, no. Uh then I'll I'll get back, I'll have a big lunch like usually like a big omelet with a bunch of salad and stuff, then go to the game win, like a very nice clean </s>
<s>[INST] guess that makes sense. I know it makes sense, but I also see a lot of evidence that he's just very charismatic in a room. So so and I've also seen, you know that's how human connections get made, like business deals get [/INST] made, how how where is this money coming from? </s><s>[INST] Oh like they rich people without blackmailing just uh like him close like him as a friend [/INST] not arguing that like okay, I like Jeffrey Epstein make sure you pull that quote. I'm a business person, I like Jeff, I </s><s>[INST] love, love, [/INST] Love, I'm in love with um this escalated quickly, I'm gonna hand over him to be my money manager to have 20% of my state fine. Where is he making the money for that? 20%. That's the thing that there's no paper trail him trading or anything. So I can understand </s><s>[INST] what Yeah, interesting. What were your [/INST] 2020 favorite moments? </s><s>[INST] You mean 2021, when you have yeah. Yeah, clearly it's just lane Maxwell trial and just really stands out to me, it's very moving, this is why I bring it up. No uh moving here. So moving, moving here. But for me I think we actually didn't cover that with you and I'd love to get your comment because you said it's for the first time in your life you moved. So it's not just about the death of the place you go to, it's the actual act of moving is also a leap. So the decision was that I'm going to give away my salary and M I. T. So stop taking salary. Give away the group. So students, no more research. The grant funding still keeping mighty affiliation. Just because I have friends and colleagues, they're still doing research but giving away really primarily is the source of money. So no salary and let it go to zero, let my bank account go to zero and uh take a leap in san Francisco or elsewhere. And as covid broke out and a lot of people started talking to me about san Francisco, about the cynicism there and I will go there and there was a kind of so it's not all the woke stuff and all that kind of things which is also a problem. It's less, it's less about dreaming about a big future about building a big future and and more about some kind of identity politics battles that they're just um you could say it's some some aspect in the positive light is important but in a place like Silicon Valley to me, the most important thing is to do big things and for that to be most of the conversation and so that cynicism was there and then I went to look at Austin and Austin it was the opposite is the optimism and you have people like as I talked to that said yuan was the optimistic about making this the capital of artificial intelligence and technology and so on. And then um Mr joe Rogan now just the optimism about making this the cultural capital of the world of uh I mean specifically comedy, but like it just radiates from them, just the excitement and uh I've seen not many people of that nature in my life and when I see that in their eyes, that engine, that fire of wanting to create something special about the place. First of all, those people rarely fail. That's first of all and second of all that is contagious and so all that combined for me, 2021 was just the the actual leap of taking the leap saying all right, well um I'm actually going to do this, so not just giving away the salary, not giving away all of that, but the whole thing, that's it, you just moved to a place, there's an empty building, you know and you're you're moving into it. Um and this is a new life and that leap, I don't know it's a scary leap to take because I've taken that leap many times in my life and this is where you know, parents and all those kinds of cynicism is really destructive because you know um from a cynical perspective is you know, I worked at google so why leave google this very high paying salary that you can have google then? M. I. T. Why leave M. I. T. Like it's M. I. T. This is you've always dreamed about like why do you get a PhD? You've loved M. I. T. You all? Why leave M. I. T. I mean this is the same process I've gone through with a lot of things in life. Like you've been saying every single stage and you need that um you need friends, you need support groups and all those kinds of things that are extremely important. But in the end it's about taking the leap. And for me, 2021 was this leap and to me that was one of the most beautiful things you can do in life, is to take those leaps. [/INST] And that's something that I think is no longer a thing in new york, there's no sense of hope. You don't go to new york. Now, if you there's been such an assault and intentionally or otherwise, maybe it's inevitable, they didn't have a choice, but there's been such an assault on creativity and small business in new york that no one, there were very few people who are in new york right now think things are gonna get great soon. Whereas here I feel it's everyday, it's just something exciting is gonna happen </s>
<s>[INST] So, but the testers to vectorized sort of formal representation, that's meaningful thing. And your intuition now, having worked with all this media is that once you are able to form that representation, you can basically take anything's any sequence. Uh Is there going back to Starcraft is their limits on the length? Uh So we didn't really touch on the long term aspect. How did you overcome the whole really long term aspect of things here? Is there some tricks or So, [/INST] the main streak. So Starcraft, If you look at absolutely every frame, you might think it's quite a long game. So we would have to multiply 22 times 60 seconds per minute times, maybe at least 10 minutes per game on average. So there are quite a few frames but the trick really was to only observe, in fact which might be seen as a limitation, but it is also a computational advantage only observe when you act and then what the neural network decides is what is the gap going to be until the next action. Um and if you look at most Starcraft games that we have in the data set that Blizzard provided, it turns out that most games are actually only, I mean it is still a long sequence, but it's maybe like 1000 to 1500 actions, which if you start looking at LST M'S large, LSD Ems transformers, it's not like it's not that difficult, especially if you have supervised learning. If you had to do it with reinforcement learning the credit assignment problem, what is it that in this game that made you win? That would be really difficult. But thankfully because of imitation learning, we didn't have to deal with this directly, although if we had to, we tried it and what happened is you just take all your workers and attack with them and that sort of is kind of obvious in retrospect because you start trying random actions. One of the actions will be a worker that goes to the enemy base and because itself play, it's not going to know how to defend because it basically doesn't know almost anything and eventually what you develop is this take our workers an attack because the credit assignment issue in a rally is really, really hard. I do believe we could do better and that's maybe research challenge for the future. Um but yeah even even in starcraft the sequences are maybe 1000 which I believe there is within the realm of what transformers can do. </s><s>[INST] Yeah I guess the difference between Starcraft and go is uh in go and chest stuff starts happening right away. So there's not yeah it's pretty easy to self play. Not easy but to self play as possible to develop reasonable strategies quickly as opposed to Starcraft. [/INST] Mean in go there's only 400 actions but one action is what people would call the God action. That would be </s><s>[INST] if you had [/INST] expand the whole third street. That's the best action. If you did mini max or whatever algorithm you would do if you had the computational capacity. But in Starcraft the 400 is minuscule. Like in 400 you don't even like you couldn't even click on the pixels around a unit. Right. So um I think the problem there is in terms of action, space size is way harder. So and that search is impossible. So there's quite a few challenges indeed that make this um kind of a step step up in terms of machine learning for humans. Maybe they're playing Starcraft it seems more intuitive because it looks real. I mean you know like the graphics and everything moves smoothly. Whereas I I don't know how to I mean go is a game that I wouldn't really need to study. It feels quite complicated, but for machines kind of maybe </s><s>[INST] it's the reverse. Yes, which shows you the gap actually between deep learning and however the heck brains work. Uh So you developed a lot of really interesting ideas. It's interesting to just ask what's the, what's your process of developing new ideas? Do you like brainstorming with others? Do you like thinking alone? Do you like uh uh like was it Ian Goodfellow said he came up with Ganz after a few beers. Uh he thinks beers are essential for coming up with new ideas. [/INST] We had beers to decide to play another game game of Starcraft after a week. So it's really similar to that story actually, I explain this, you know, in a deepmind retreat and I said this is the same as the gun story. I mean we were in a bar and we decided let's play again next week and that's what happened. </s><s>[INST] I feel like we're getting the wrong message to young undergrads. Yeah, but in general like yeah, like brainstorming, do you like thinking alone, working stuff out? And so [/INST] I think, I think throughout the years also things changed, right? So initially I was very fortunate to be um with great minds like Geoff Hinton, Jeff Dean aliases keeper. I was really fortunate to join Brain at a very good time. So at that point, ideas, I was just kind of brainstorming with my colleagues and learned a lot and keep learning is actually something you should never stop doing, right. So learning implies reading papers and also discussing ideas with others. It's very hard at some point to not communicate that being reading a paper from from someone or actually discussing, right? So definitely that communication aspect needs to be there whether it's written or oral. Um nowadays I'm also trying to be a bit more strategic about what research to do. So I was describing a little bit this sort of tension between research for the sake of research and then you have on the other hand, applications that can drive the research, right? And honestly the formula that has worked best for me is just find a hard problem and then try to see how research fits into it, how it doesn't fit into it and then you must innovate. So I think machine translation drove sequence to sequence. Um then maybe like learning algorithms that had to like communitarian algorithms led to point our networks, um Starcraft led to really scaling up imitation learning and the alpha star league. So that's been a formula that I personally like, but the other one is also about it and I seen it succeed a lot of the times where you just want to investigate model based RL as as kind of a research topic and then you must then start to think well how are the tests, how are you going to test these ideas. Um you need to kind of a minimal environment to try things. You need to read a lot of papers and so on and that's also very fun to do and something I've also done quite a few times, both brain and the mind and obviously as a PhD. So, so I think besides that the ideas and discussions, I think it's important also because you start sort of guiding not only your own goals, but other people's goals um, to the next breakthrough. So you you must really kind of understand these, you know, feasibility. Also, as we were discussing before, right, whether whether this domain is ready to be tackled or not and you don't want to be too early, you obviously don't wanna be too late. So it's it's really interesting um this strategic component of research, which I think as a grad student, I just had no idea. You know, I just read papers and discussed ideas and I think this has been maybe the major change and I recommend people kind of fit forward to success how it looks like and try to backtrack other than just kind of looking out. This looks cool, this looks cool. And then you do a bit of random work which sometimes you stumble upon some interesting things, but in general, it's also good to plan a bit. </s>
<s>[INST] Um I [/INST] wonder how big of a part because also with </s><s>[INST] with Ernest Becker the [/INST] idea is that we're all trying to achieve </s><s>[INST] an illusion of immortality. [/INST] Yeah, so we're trying to create </s><s>[INST] something that outlasts [/INST] us and therefore </s><s>[INST] we create bigger and bigger [/INST] things in societies </s><s>[INST] and bridges and. [/INST] Yeah, well I think what's what's </s><s>[INST] what's missing from Becker's [/INST] analysis is uh </s><s>[INST] you know I mean [/INST] it's a it's a </s><s>[INST] fascinating book to read [/INST] denial of death </s><s>[INST] but what's missing is that [/INST] I think that the reason that and again I think it's more men than women. I think there's a sex difference on this that men uh I want to build a </s><s>[INST] lasting legacy [/INST] because that will </s><s>[INST] in turn [/INST] affect their lineage. Um And uh although I I do now woody Allen is </s><s>[INST] out of favor, but I remember [/INST] this quote from him, he said, he said he didn't want to achieve immortality through his work. </s><s>[INST] He wanted to achieve [/INST] immortality by not dying. Oh </s><s>[INST] boy. [/INST] The the funny ones </s><s>[INST] are also uh [/INST] deeply flawed. </s><s>[INST] Often [/INST] staying on the topic of sex differences </s><s>[INST] in a very different way. Perhaps. So [/INST] dominance </s><s>[INST] and submissiveness. [/INST] Something you've also </s><s>[INST] written about. What's the [/INST] role of that inside relationships about this </s><s>[INST] human dynamic [/INST] of dominance </s><s>[INST] and submissiveness. Um Is that a feature or a bug? So the the stable [/INST] state that these </s><s>[INST] dynamical systems arrive [/INST] at, it's a good </s><s>[INST] to have [/INST] an </s><s>[INST] equality within a relationship or is it good to have differences [/INST] in relationship? </s><s>[INST] Are you talking about [/INST] romantic relationships or just in human </s><s>[INST] relationships? Romantic? Probably because unless it could be generalized to human relationships, perhaps it could be generalized in [/INST] human relationships. I </s><s>[INST] wasn't thinking that, but perhaps it could be. But let's start start [/INST] with Romantic. </s><s>[INST] I guess one on 1. I'm [/INST] personally in favor of </s><s>[INST] equality [/INST] on that dimension within </s><s>[INST] romantic relationships. [/INST] And um in </s><s>[INST] the in [/INST] don't talk about my personal </s><s>[INST] life but [/INST] um but I've been in relationships and </s><s>[INST] the best ones tend to be those [/INST] where where there's </s><s>[INST] equality and [/INST] More one person does not dominate the other. </s><s>[INST] Um [/INST] But I guess what I was, the reason I ask you is and what type of </s><s>[INST] relationships because [/INST] there's some um things </s><s>[INST] like coalitions [/INST] where </s><s>[INST] hierarchy [/INST] is very </s><s>[INST] important to the function of [/INST] the coalition. So it's </s><s>[INST] like you if you're like a [/INST] war coalition or something in small </s><s>[INST] group warfare, you [/INST] can't just have equality. You have to have um leaders that are </s><s>[INST] determining the [/INST] the battle plan, so to </s><s>[INST] speak. [/INST] Um And so if you have your your </s><s>[INST] your [/INST] attacking a neighboring group </s><s>[INST] or something and everyone gets an equal, [/INST] say it's it's not gonna work that way. And so we tend to um appoint as </s><s>[INST] leaders. Those who [/INST] are it doesn't always work out well but </s><s>[INST] those who are presumably [/INST] wise or good effective leaders and even talk about and I'm sure </s><s>[INST] you're familiar [/INST] with this and I'm not an expert </s><s>[INST] on this, but you know [/INST] wartime leaders versus peacetime leaders. And so </s><s>[INST] again it depends [/INST] on </s><s>[INST] you know what the [/INST] goal is of the group that you are a part of. And so and so I think there is functionality and utility to a lot of our evolved </s><s>[INST] psychology [/INST] of status and dominance and submissiveness. So for example, and you have to </s><s>[INST] look at the individual psychology [/INST] and this is actually something I'm currently studying. Um Again with with Patrick Durkee </s><s>[INST] uh [/INST] where </s><s>[INST] one advantage [/INST] of the status </s><s>[INST] hierarchies is that you're [/INST] not always </s><s>[INST] battling, [/INST] you know, so you </s><s>[INST] determine. [/INST] Um And that's why here's </s><s>[INST] another sexually [/INST] D'amore Fick aspect </s><s>[INST] of our psychology formidability [/INST] assessment. So there's there's evidence </s><s>[INST] that [/INST] males engage in this. You know, can I take this guy or can he </s><s>[INST] take me Like and it's like a spa [/INST] it's it's like a spontaneous </s><s>[INST] assessment of [/INST] of formidability and and </s><s>[INST] it also [/INST] that information is </s><s>[INST] critical because that means [/INST] like who you should </s><s>[INST] not challenge [/INST] or or if you who you can challenge with </s><s>[INST] impunity, impunity. So [/INST] um and and there's functionality </s><s>[INST] to submitting [/INST] as well, </s><s>[INST] you know, because [/INST] you you defer </s><s>[INST] to someone [/INST] so that </s><s>[INST] you don't get vanquished [/INST] and you live to see another day. </s><s>[INST] Uh [/INST] So I think we </s><s>[INST] actually have a very rich psychology of [/INST] status hierarchies and dominance and </s><s>[INST] submissiveness. So [/INST] especially sort of </s><s>[INST] violent conflict. Yes. But back to [/INST] relationships. </s><s>[INST] So [/INST] maybe he phrased another </s><s>[INST] way, [/INST] what is masculinity? </s><s>[INST] What is femininity? Is there value inside a [/INST] relationship for for </s><s>[INST] differences? You [/INST] talked about meetings, </s><s>[INST] meeting [/INST] meeting strategies </s><s>[INST] with the dating [/INST] stage where you're selecting the mate, </s><s>[INST] but also within, you know, mating [/INST] broadly defined </s><s>[INST] as the entirety of the [/INST] process. </s><s>[INST] Are should those differences be magnified and celebrated or um [/INST] sort of suppressed. </s><s>[INST] I've [/INST] seen enough different relationships work. And I've seen enough </s><s>[INST] relationships [/INST] implode too. </s><s>[INST] Say there's no there's [/INST] not one size fits all on on these things. So even with respect to masculinity and femininity, um some </s><s>[INST] reduced psychologically [/INST] to two </s><s>[INST] other terms [/INST] which our agency and communion. So where agency is, you know, are you instrumental goal oriented? </s><s>[INST] Um get [/INST] tasks done etcetera. Communion is, you know more the </s><s>[INST] love and forming [/INST] connections with other people and so forth. Um </s><s>[INST] And [/INST] I published </s><s>[INST] a study a while back on on [/INST] what's were called </s><s>[INST] unmitigated agency [/INST] and </s><s>[INST] unmitigated communion. [/INST] So you they're like </s><s>[INST] good and [/INST] bad aspects of </s><s>[INST] agency and [/INST] Communion so they </s><s>[INST] can go, so there's toxic, as they say, masculinity, toxic femininity. You can just rephrase that saying there could be toxic agency and toxic communion. Yeah. [/INST] Yeah. And so and so some </s><s>[INST] elements of [/INST] masculinity, uh the unmitigated </s><s>[INST] masculinity [/INST] is, I think </s><s>[INST] terrible. I was actually walking [/INST] around downtown </s><s>[INST] Austin earlier today, just [/INST] give this example. And this guy </s><s>[INST] um [/INST] was, I guess stuck and wanted the car ahead </s><s>[INST] of him to move, [/INST] and all of a sudden he screamed </s><s>[INST] out of his move your [/INST] fucking car. </s>
<s>[INST] had some common something. Yeah, it's funny because on the surface, I think we're different in a lot of ways, but there's something, Yeah, I mean that's [/INST] just constant. There you go afternoon. So I will tell the story of how we met and I'll let Michael tell the story of how we okay, okay, so here's how we met. Um I was already at at that point it was 18 C Labs has a long interesting story there. But anyway, I was there and Michael was coming to interview. He was a professor at Duke at the time, but decided for reasons that he wanted to be in New Jersey. Uh and so that would mean Bell Labs slash 18 T labs. Uh and we were doing the interview interviews very much like academic interviews. Uh and so I had to be there. We all had to meet with him afterwards and so on one on one, but it was obvious to me that he was going to be hired Like no matter what because everyone loved him. They were just talking about all the great stuff he did. Oh I did this great thing and you just won something at Triple AI think or maybe you got 18 papers in Tripoli. </s><s>[INST] I got the best paper award it to play I for the crosswords. [/INST] Right? Exactly. So that it all happened and everyone was going on and on and on about actually tender was so incredibly nice things about you. Really? Yes. So he can </s><s>[INST] be very grumpy. Yes, that's nice to [/INST] hear. He was grumpily saying very nice things, that it does make sense. So, you know, so it was going to come. So why were we, why was I meeting him? I had something else. I had to do a camera. What it was probably involved comments. </s><s>[INST] Remember meeting me as inconveniencing his afternoon. [/INST] So he came, so eventually came to my office, I was the middle trying to do something, I can't remember what and he came and he sat down and for reasons that are purely accidental, despite what Michael thinks. My desk at the time was set up in such a way that is sort of an L shape and the chair on the outside was always lower than the chair that I was in. And you know, the kind of point was the only </s><s>[INST] reason I think that was on purpose is because you told me it was on purpose. I don't [/INST] remember that. Anyway. The thing is that, you know, it kind of, his </s><s>[INST] guest chair was really low so that he could, he could look down at everybody. The idea [/INST] was just to simply create a nice environment that you were asking for a mortgage. And I was going to say no, that was a very simple idea here. Anyway, so we said that we just talked for a little while and I think he got the impression that I didn't like him. It wasn't true, strongly got the talk was really good. And by the way it was </s><s>[INST] terrible. And after right after the talk, I said to my host Michael Kearns, who ultimately was my boss. I'm a friend and a huge fan of Michael. Yeah, yeah, he is a remarkable person. Um I after my talk today, I went into the um, racquetball. He's good at basketball. No, but basketball, racquetball squash, squash, [/INST] squash, racquetball squash, which is not racquetball, Yes, squash. No, and I hope you you hear that Michael </s><s>[INST] u as a game, not his skill, because I'm pretty sure he's alright, there's some competitiveness there. But the point is that there was like the middle of the day I had full day of interviews, I met with people, but then in the middle of the day I gave a job talk and then um and then there was going to be more interviews, but I pulled Michael aside and I said, I think it's in both of our best interest if I just leave now because that was so bad that it's just be embarrassing if I have to talk to any more people like you look bad for having invited me, like it's just let's just forget this ever happened. So I don't think the talk went well, [/INST] it's one of the most Michael lippman set of sentences I think I've ever heard he did great, or at least everyone knew he was great. So maybe didn't matter, I was there, I remember the talk and I remember him being very much the way I remember him now on any given week. So it was good. And we met and we talked about stuff. He thinks I didn't like him because he </s><s>[INST] was so grumpy. Must be in the chair thing, the chair thing and the low voice I think like obviously and that like that like slight like skeptical look. Yes, I I have no idea what you're talking about. [/INST] Probably didn't have any idea what you were talking about. Anyway, I liked him. He </s><s>[INST] asked me questions, I answered questions, I felt bad about myself. It was a normal day, [/INST] normal candy left </s>
<s>[INST] So we found a way to fix our own nitrogen for ourselves here in the schnapps. What's in the cocktail? Yeah, but that's way after the original invention of hydrogen. Oh, absolutely. Absolutely. [/INST] And without that, we wouldn't have all the steps of evolution along the way. Oh, absolutely. Absolutely. Oh, absolutely. We tried to replicate, in the most simplest way, what nature has come up with. We do this by taking nitrogen using a lot of pressure and then generating ammonia. Life does this in a more sophisticated way, relying on one single enzyme called nitrogenase. It's the nitrogen that is used together with 8-electron donor and ATP, together with a lot of hydrogen. Life pushes this metabolism down to create fixed nitrogen. </s><s>[INST] It's quite remarkable. So the lab pet, E. coli, inject them with DNA, those E. coli does nitrogen fixing in part? [/INST] Or is that a different one? So some biological engineers engineered E. coli to fix nitrogen, I believe. Not us. We used the nature's nitrogen-fixing bug and engineered it with the nitrogen-fixing metabolism </s><s>[INST] that we resurrected using our computational and phylogenetic tools. How complicated are these little organisms? [/INST] What are we talking about? </s><s>[INST] It depends on how we define complicase them. So I can tell that you appreciate and respect the full complexity of even the most seemingly primitive organisms, because none of them are primitive. That said, what are we talking about? What kind of machineries do they have that you're working with when you're injecting [/INST] them with DNA? So I will start with one of the most fascinating machineries that we target, which is the translation machinery. It is a very unique subsystem of cellular life in comparison to, I would say, metabolism. And we used to, when we are thinking about cellular life, we think of cell as the basic unit or the building block. But from a key perspective, that's not the case. One may argue that everything that happens inside the cell serves the translation and the translation machinery. There is a nice paper that called this that the entire cell is hopelessly addicted to this main informatic computing biological chemical system that is operating at the heart </s><s>[INST] of the cell. Which is the translation? It is the translation. What's the translation from what to what? [/INST] So RNA to enzymes? It is the translation. It converts a linear sequence of mRNA into a later folded protein. It's when that's the core processing center for information, for life. It has multiple steps. It initiates, it elongates, it terminates, and it recycles. It operates discrete bits of information. It itself is like a chemical decoding device, and that is incredibly unique for translation </s><s>[INST] that I don't think you will find anywhere else in the cell that does this. So even though it's called translation, it's really like a factory that reads the schematic and builds a three-dimensional object. It's like a printer. [/INST] I would divide it into actually even four more additional steps or disciplines than what would it take to study it the way you described it. It's a chemical system, it's the compounds that make it up are chemicals. It's physical, it tracks the energy to make its job, to do its job. It's informatic. What is processed are the bits. It's computational. The discrete states that the system is placed when the information is being processed. That itself is computational. And it's biological. It's there's variability and inheritance that come from imperfect replication even and imperfect computation. </s><s>[INST] Man, that's so good. From the biology comes the... When you mess up the bugs or the features, that's the biology. Informatics is obvious in the RNA, that's a set of information there. The different steps along the way is actually kind of what the computer does with bits, stone computation, physical, there's almost like a mechanical process to the whole thing that requires energy and actually it's manipulating actual physical objects and chemicals because [/INST] you have to ultimately it's all chemistry. Yeah, and it tracks this information. It is almost a mini computer device inside ourselves. That's the oldest computational device of life. </s><s>[INST] It's likely the key operation system that had to evolve for life to emerge. It's more interesting or it's more complicated in interesting ways than the computers we have today. I mean, everything you said, which is really, really nice, I mean, I guess our computers have the informatic and they have the computational, but they don't have the chemical, the physical [/INST] or the biology. Exactly. And the computers don't link information to function, right? They are not tightly coupled, nowhere close to what translation or the way translation does it. So that's the number one, I think, difference between the two. </s><s>[INST] And yes, it's informatic and we can discuss this further too. One hundred percent. Let's please discuss this further. Which part are we discussing for each one of those are fascinating worlds. [/INST] Each of the five. Yeah. So, well, we can start with the more, I guess, the ones that are more established, which is the chemical aspect of the translation machinery. The specific compounds make up the assembly of RNA chemists show this in many different ways. We can rip apart the entire machinery. We know that at the core of it, there is an RNA that operates not only as an information system itself or information itself, but also as an enzyme. And origin of life chemists make these molecules easily. Now we know we can manipulate RNA, we can make even the single pot chemistries, we can create compounds. What's a single pot chemistry? I would say when you add all the recipes that you know, that will lead you to the final product. </s><s>[INST] This is what original life chemists do is they come up with this pot, they throw a bunch [/INST] of chemicals in, and they try to, they're basically chefs of a certain kind. I'm not sure if that's what they call it, but that's how I think of it. Because it is all combined in a test tube, and you know the outcome, and it's very mathematical. Once you know the right environment and the right chemistry that needs to get into this container or this pot, you know what the outcome is. There's no luck there anymore. </s>
<s>[INST] And outsourced and automated human resources HR solution for [/INST] businesses I </s><s>[INST] think in the video on their [/INST] website it </s><s>[INST] says that many businesses would need to hire an HR person and that's [/INST] like </s><s>[INST] 70 K a year plus. So what they're offering is super cost effective because it's just $99 per month and they take care of the HR compliance and all the complexities involved with that. It's important to hire people that can take care of human resources. HR is one of those things that when done poorly. It can really hurt and when done well, it just makes everything work beautifully and so you should use the best tools for the job and uh really cost effective. One is Bambi. You can schedule your free conversation today. Go to Bambi dot com and type lex on the podcast When you sign up, it's spelled B A M B E. This show is also brought to you by Inside Tracker a service. I used to track biological data. It's kind of interesting to think of the human body as just the source of signals. You got a hierarchy of living organisms, millions of them, billions of them, depending how you define the atomic organisms that make up the human body. And so all of them are sending signals, tiny signals, big signals and all of those that conglomerate that orchestra sends just a huge amount of data which is used by the brain and the nervous system and the immune system and all the different systems that make up the anatomy and the physiology of the body to sort of coordinate everything. And for us to plug in and collect some of that data in order to make lifestyle and health recommendations. I think that's [/INST] the future </s><s>[INST] recommendation should be done based primarily in your body, grounded of course, in the wisdom that science provides for the population. Anyway, Inside Tracker is a step into that direction. It's a preview of the future. Get special savings for a limited time. When you go to Inside Tracker dot com slash lex. That's Inside Tracker dot com slash lex. This show is also brought to you by net suite and all in one cloud business management system. They manage financials, inventory, e commerce, all the different business related details the ad reads today. And it's funny because it's on the mammoth episode and timothy is one of the greatest business leaders and minds and investors and vcs and technologists, engineers and just intellectuals honestly that I've ever listened to and gotten a chance to interact [/INST] with really </s>
<s>[INST] Do you draw any parallels with our time, and what are some key differences? There's been contested elections, Florida, Florida, Florida, with Al Gore, and there's been just contested election after contested election, and of course, most famously recently [/INST] the contested election that led to January 6. So I think a couple of parallels and a couple of differences. One parallel is that when you have close elections, the losing side is never happy. It's a myth that when you have a close election, the other side just accepts it. And it's not, that doesn't happen. And we need to be attentive to that and ready for that. January 6 actually should surprise us not because it happened, but because it hadn't happened before. People who lose a close election are never happy and they always think that something has been done. That's one parallel. Second parallel is elections are violent. We have this myth that our elections are peaceful. There's always violence involved in one way or another, violence in either trying to prevent people from voting or violence in preventing people from preventing people from voting, right? Elections are not peaceful walks in the park. And that's why most countries have a centralized system to manage elections and provide protection for people. We need to think about that. A lot of people don't vote because they're afraid they don't want to take the time, but they're also afraid that they're going to anger someone or that they're going to be seen as politicizing an issue. Differences. In 1876, there was fraud in the election. There were people who voted two, three times. One of the things the Ku Klux Klan did is it prevented black people from voting and that it helped white people go to multiple voting booths. And this was quite common. In the 1880s, if you went to vote, here's how it would happen in a place like Chicago and New York. The union boss from your factory would come and get you at the factory, give you lunch, get you drunk, and then drive you from one voting booth to another and give you a ballot that you would bring in and just, and he would watch you deposit that ballot. Sounds pretty nice. Not going to lie. I take that ride. So that's a difference. That is not how our elections work now. One of our great accomplishments has been to eliminate virtually all the fraud in our elections. How have we done that? By creating safeguards. It is very difficult. All the evidence we have is that the minimal fraud that's occurred in elections are onesies and twosies, and it's never in the last 20 years had any big difference in the outcome of elections. So that's a big difference. And then another big difference, I think, is that in that time, the Democrats and Republicans are on the opposite sides of where they are now, and that changes everything. So the Democrats then are the party of the Confederacy. The Democrats are the party of exclusion. The Republicans are more the party of economic expansion. And the Republicans are the big </s><s>[INST] ten party. We're reversed today. Do you think because there's much less election fraud now, like you described, one of the lessons we want to maybe learn from that is there doesn't actually have to be election fraud for either side to claim there's election fraud. It seems like it's more and more common. And it seems to me that in 2024 election in the United States, if a Republican wins, there would also be just maybe just as likely as if a Democrat wins, that there would be nuanced [/INST] claims of election fraud because it's become more and more normalized. I think what this history shows is that our election system makes it easy for people to claim fraud because it's so unnecessarily complex. First of all, we don't have a system where the person who gets the most votes is necessarily the winner. So that already creates one problem. Second problem is everything I talk about this in the book is controlled at the county level. So what happens with Hayes and Tilden in 1876 is you have one county official who says they think one person won, another county official thinks says the other person won, there's no centralized system. It would be as if we allowed every airport to control safety and airplanes, our airplanes would not be safe. Our airplanes are safe because the FAA and the National Transportation Safety Board have strict universal guidelines for what makes for a safe plane and therefore our planes generally don't fall out of the sky. Our system is very complex. It has complex rules and has too many people who have authority in too many different places. Complexity makes it easier for someone to make an argument that the wrong thing has been done. We should simplify the system. In Brazil, they had a very close election and it's very hard for Bolsonaro who lost that close election to claim there was fraud because there's a central authority run by the judiciary that counted the votes and it's just simple. It's not about which states, it's not about who the county officials were. Did he claim or no? </s><s>[INST] He has not acknowledged that he lost. To push back on your statement, I'm undefeated in monopoly and risk because anytime I lose, I walk away claiming there was fraud and cheating involved and I refuse to believe otherwise. I just think that accusations of fraud is [/INST] a narrative that's disjoint from the reality of whether there was or not fraud. I agree, but I think we make it a little easier for that narrative by having a complex convoluted </s>
<s>[INST] the way, I'm not saying that this is what's happening here, but but there's uh, there's probably an excitement to playing God 2 2 and getting away with it. Like [/INST] I know people, I know adults grown adults who are successful in their fields and they they cheat, they cheat in lessons, they cheat and like I've I don't want to have taught any may I may or may not have uh for some reason one of them watches this and they know they're guilty. Uh and it happens, it happens not just teenagers, not just young adults, but full grown adults will cheat when they play because they think it helps them learn. </s><s>[INST] Oh well that's exactly just that justification. But I just meant like it might not be just about winning. It might also just feel good to have that power. Like I bet you it's a drug. I mean like with a lot of criminals with a lot of criminals? I feel like part of like the like mass murderers and serial killers. I feel like a lot of it is they can get away with it. The the fact that they like they like everyone else is a sucker and they figured out how to do this evil thing and obviously cheating is nowhere close to that. But but there's still a feeling of getting away with it. Yeah. I wonder you're pretty objective on the whole thing where if you were um a betting man, what would you say is the probability? And are you changing day by day in your head? What's the probability that hans cheated over the board against magnus in the in ST louis [/INST] That's a tough one man. </s><s>[INST] Have you even allowed yourself to put a probability on it? [/INST] No, not on that specific game. Because I think a lot of that game was affected by magnus zone psyche. That was one of his worst games ever. </s><s>[INST] So he played poorly to magnus play, which [/INST] doesn't help his case. Hans might have cheated in that game, but we'll never know. I I think day by day the evidence is slowly starting to show more and more that he's cheated. Like, like how Magnus said more than he said and more recently, it's undeniable, like, right, a lot of the statistics are there? The problem is you can't prove you're not cheating. Yeah. Unless you strip naked like that site offered him $1 million bucks to like everything about the </s><s>[INST] which site [/INST] Headline that said was offered $1 million bucks and where I struggled to comprehend this, how on earth he could pull it off and like I'm a guilty that my brain goes to guilt first and resent resentment, remorse, guilt. That kind of that trio </s><s>[INST] um magnus put out a statement as we speak yesterday saying, dear chess world at the 2022 sink field cup, I made the unprecedented professional decision to withdraw from the tournament after my round three game against Hans Nieman a week later, during the Champions Chess tour? I resigned against hans Nieman after playing only one move. I know that my actions have frustrated many in the chess community. I'm frustrated. I want to play chess, I want to continue to play chess at the highest level in the best events. I believe that cheating chess is a big deal and an existential threat to the game. I also believe that chess organizers and all those who care about the sanctity of the game we love should seriously consider increasing security measures and methods of cheat detection for over the board chess. When Neiman, I was invited last minute to the 2022 Sink Field Cup, I strongly considered withdrawing prior to the event I ultimately chose to play. That's the thing you're referring to is that he can like now we know he was torn about the whole thing. I believe that Neiman has cheated more and more recently than he has publicly admitted his over the board. Progress has been unusual and throughout our game in sync field cup, I had the impression that he wasn't tense or even fully concentrating on the game in critical positions while out playing me as black in a way, I think only a handful of players can do this game contributed to changing my perspective he must do. We must do something about cheating. And for my part going forward, I don't want to play against people that have cheated repeatedly in the past because I don't know what they're capable of doing in the future. There's more than I would like to say. Unfortunately at this time I'm limited in what I can say without explicit permission from Neiman to speak openly. So so far I have only been able to speak with my actions and those actions have stated clearly that I'm not willing to play chess with Neiman. I hope that the truth in this matter comes out, whatever it may be sincerely magnus Carlsen, World chess champion. Um I [/INST] was used to sign off your statements </s><s>[INST] if I was a [/INST] world No, I'm just saying whatever lex Fridman, what would be the </s><s>[INST] title? Yeah, I don't know. I think I would not, [/INST] even </s><s>[INST] if I was a world champion, I would just say lex or make up a title and I feel like I really fucked up in life If I have to tweet a statement as an image that's like when you get you're a politician, you got caught cheating on your wife like for many years in a row, then I tweet an image, I'm sorry for all the people I have hurt and the people that believed in me and whatever else. And then I would sign world chess champion, [/INST] you know the most like the modern way to give a statement what I thought magnus was gonna do. I thought he was going to write on the recent scandal or my statement in the past few weeks tweet </s>
<s>[INST] So the goal is essentially to find and exploit in a system that allows you to run shell to run arbitrary code on that system. [/INST] That's one of the categories. That's like the portable category. </s><s>[INST] Uh potable, [/INST] potable. It's like, you know, you pone the program you uh it's a program. </s><s>[INST] Uh Yeah. You know, first of all I apologize, I'm gonna I'm gonna say it's because I'm rushing but maybe you can help educate me. Um [/INST] Some video game like misspelled own way back in </s><s>[INST] the. Yeah. And there's just, I wonder if there's a definition and I have to go to urban dictionary for it. Okay, so what was the heyday city by the way? But was it, what decade are we talking about? I [/INST] think like I mean maybe I'm biased because it's the error that I played but like 2011-2015 because the modern CTF scene is similar to the modern competitive programming seen. You have people who like do drills, you have people who practice and then once you've done that you've turned it lesson to a game of generic computer skill and more into a game of. Okay, you memorize, you drill on these five categories. Um And then before that it wasn't uh it didn't have like as much attention as it had. I don't know they were like I won $30,000 once in Korea for one of these competitions </s><s>[INST] crab. Yeah they were they were so that means I mean money is money but that means it was it was probably good people there. Exactly. Yeah. Are the challenges human constructed or are they grounded in some real flaws and real systems usually [/INST] they're human constructed but they're usually inspired by real flaws. </s><s>[INST] What kind of systems I imagine is really focused on mobile? Like what has vulnerabilities these days? Is it primarily mobile systems like uh android? [/INST] Everything does. Yeah of course the price has kind of gone up because less and less people can find them. And what's happened in security is now if you want to like jailbreak an iPhone you don't need one exploit anymore. You need nine </s><s>[INST] nine chained together. What you mean? Yeah wow. Okay. So it's really what's the what's the benefit? Speaking higher level philosophically about hacking? I mean it sounds from everything I've seen about you, you just love the challenge and you don't want to do and you think you don't want to bring that export out into the world and doing the actual uh let her run wild. You just want to solve it and then you go on to the next thing. [/INST] Oh yeah I mean doing criminal stuff. It's not really worth it and I'll actually use the same argument for why I don't do defense for why I don't do crime If you want to defend a system? Say the system has 10 holes, right? If you find nine of those holes as a defender, you still lose because the attacker gets in through the last one. If you're an attacker, you only have to find one out of the 10. But if you're a criminal, if you log on with a VPN nine out of the 10 times at one time, you forget you're done </s><s>[INST] because you're caught because [/INST] you only have to mess up once to be caught as a criminal. That's why I'm not a criminal. </s><s>[INST] But okay, let me, because I was having a discussion with somebody, uh, just at a high level about nuclear weapons, actually why we're having blown ourselves up yet. And my feeling is all the smart people in the world. If you look at the distribution of smart people, smart people are generally good and then this other person is talking to Sean carroll, the physicist and you were saying no good and bad people are evenly distributed amongst everybody. My sense was good. Hackers are in general, good people and they don't want to mess with the world. What's your sense? I'm [/INST] not even sure about that? Like have a nice life crime wouldn't get me anything. Okay. But if you're good and you have these skills, you probably have a nice life too, </s><s>[INST] right? Like you can use the father things, But is there an ethical, is there some, they're a little voice in your head that says of, well, yeah, if you could hack something to where you could hurt people and you could earn a lot of money doing it though. Not hurt physically perhaps, but disrupt their life in some kind of way. Is there a little voice that says [/INST] um well, two things, One, I don't really care about money, so like the money wouldn't be an incentive. The thrill might be an incentive, but and I was 19, I read crime and punishment. That was another, that was another great one that talked me out of ever really doing crime um because it's like that's gonna be me, I'd get away with it, but it would just run through my head even if I got away with it, you know, and then you do crime for long enough, you'll never get away with </s><s>[INST] it right in the end. That's a good reason to be good. [/INST] I wouldn't say I'm good, I just am not bad. </s><s>[INST] You're a talented programmer and a hacker in a good positive sense of the world award. You've played around found vulnerabilities in various systems. What have you learned broadly about the design of systems and so on from that from that whole process. [/INST] You learn to not take things for what people say they are, but you look at things for what they actually are. Mhm. Yeah, I understand that's what you tell me it is, but what does it </s><s>[INST] do? And you have nice visualization tools to really know what it's really doing. Oh, I [/INST] Wish I'm a better programmer now than I was in 2014. I said Kira, that was the first tool that I wrote that was usable. I wouldn't say the code was great, I still wouldn't say my code is great. </s>
<s>[INST] interaction relate to the uh the morphing of the human experience and deeply understanding that perhaps there's no equations yet for that kind of thing. You really have to build up intuition by experiencing it and over time and sort of subjective self report, like trying to build [/INST] an understanding </s><s>[INST] of the effects of the different chemistries. [/INST] Yeah. Yeah, you can you can have approximate ideas but to know exactly. So, you know, when I first tried M. D. M. A. Which was 1982 and this was after I had done um lots of LSD and mescaline yeah, and mushrooms. Um I was shocked at how different it was than these other substances and yet how profound it was. So are there a whole new kind of categories of classes of drugs that were not aware of? That would be not so much this um like eco dissolution or emotional what M. D. M. A. Does is reduces activity in the amygdala. The fear processing part of the brain. So it's not just chemistry but it routes energy throughout the brain in a different way. It increases activity in the prefrontal cortex. So you think more logically the that I think has an enormous impact on the effect of M. D. M. A. Um The other thing it does is it increases connectivity between the amygdala and the hippocampus. So it helps facilitate um processing of things into long term memory. Um And with ptsd trauma is like never in the past it's always about to happen. So will we one time develop drugs that would even be specific to certain kind of memories? We're working with a woman Rachel Yehuda who is um at the Bronx V. A. And she's done some studies that are with the epa genetics of trauma. So she's worked with holocaust survivors and their Children and she has identified um epigenetic mechanisms by which trauma is passed from generation to the generations sort of like set points for anxiety, fear, certain things like that. But the question is can you actually transmit memories from one generation to the next. Now this is not um D. N. A. Uh changes which happened over a very long period of time and the evolutionary scale but within one lifetime within some experiences you're epigenetic what turns on the genes or turns off certain genes that can be impacted. And that's what we know now can be transmitted from generation to generation. Either by the father or the mother through the sperm or the egg. So it's it's pretty remarkable. So what what Rachel's gonna try to do is M. D. M. A. Research for PTSD and look at these epigenetic markers before and after and see if they change as in the consequence of therapy. So will we develop one day certain kind of chemicals that will be able to bring certain kind of memories to the surface. Um That's not inconceivable. </s><s>[INST] The epigenetic angle is fascinating that there would be these epigenetic perturbations that lead to memories living from one generation to the other and then bringing those memories to the surface and using um using that a signal to understand what exactly the psychedelics bring to the surface and not. [/INST] Yeah. Now the other part portion of that those culture, I mean culture is where we store all these memories and the stories that we get passed out. </s><s>[INST] Especially with a lot of shared you talk about the holocaust of World War Two where it is um it's deeply ingrained in the culture the impact of those events and sort of an aggregate the different perspectives on that particular event create a set of stories that you can plug into and then uh they kind of resonate with some aspect of you. That creates a memory that's connected to like when I think about World War Two and the holocaust, I think about my own family, but in some sense, it's also resonating with stories of many others. So it's like somehow the two echo each other and I'm just providing my own little flavor on top. The meat of the stories are probably those that are shared with others. It's plugging into the collective unconscious. That's um that's really fascinating, really plugging into like precisely plugging into particular memories as a way to uh to deal with trauma and ptsD that kind of thing. [/INST] I'll just have that the most important dream of my life ever was of a holocaust survivor, telling me that he was miraculously saved from death. Um and he knew that he was saved for a particular purpose, but he never knew what that purpose was. So, in the dream, I'm seeing him on his deathbed and um and then he shows me whatever happened to him during the holocaust, you know? And then um we're back in the room on his deathbed and he says, well I know what my purpose was now, and I'm like, oh great, what was it he said to tell you to be a psychedelic therapist, study psychedelics and bring back psychedelic research and I thought to myself, I've already decided to do this. You can lay this on me, I can say yes, and then you can die in peace. And then he died in front of my eyes in the dream. So I think that that kind of cultural um transmission that I got from when I was really young, you know, then manifested in this dream and that was this story about how people can be um incredibly vicious and can be very motivated by um irrational factors. And so I just feel that this this kind of multi generational transmission of the story of the irrational, you know, being a murderous factor. Um and something I needed to respond to um was deeply ingrained and I would say, my guess is, you know, more culturally than this epigenetic mechanism. </s>
<s>[INST] there an element to, there's a beautiful weirdness to you as a human being? Was there was there uh Like a pressure to conform ever to hide yourself from the world or or the $12,000 and the acid give you the confidence you needed to be yourself. [/INST] Oh no, I don't, like I still I know, I I think sure there's that pressure and like, you know whenever you're, you're beginning to really differentiate from your parents, but then you go back to hang out with your parents, you can feel that it's not like they even want you to conform, but you'll just, you could slip into that whatever that was. So I remember that when I would go back and like visit them and stuff and surely conformity or the pressure to like not be individual or whatever. It's, it's everywhere man. </s><s>[INST] Do you think you made your parents proud? [/INST] No, </s><s>[INST] no, no, no. [/INST] Well I think that um when my mom died, I felt successful in the sense that I was able to support my, I was I was making money from doing stand up and my I didn't need help. I was like, as I was supporting myself with art and doing good, what I thought was great then, So, and I think she like, because she had witnessed me literally failing, I mean, which is by the way, I think part of you want to be an artist or successful, you you kind of have to fail like there if if, and if there was a guaranteed route from sucking to not sucking or from like the neophyte phase of whatever the art form is and, you know, some intermediary phase and I think a lot more people would do it, but there really is no guarantees. And, and especially the stand up comedy, it's like, you'd have to be a maniac to want to think that that's gonna work out for you, you have to, so you're gonna, there are obviously exceptions, but for me it was like a long slog, you know, and that's scary for a mom. So, but that being said when she was dying, like she did recognize that I was like, not slogging anymore and she did say she said you did it and that's cool. But, and you know, I would love her to see me now. Like, now would be way cooler. But maybe she does. I don't know. </s><s>[INST] She's listening to your podcast elsewhere and the other in [/INST] the bardo. </s><s>[INST] Yeah. However long that lasts, Reconfiguring the whole process to start again. Um You as a father? No. How did that change you? [/INST] Yeah, that's the big change, man. That's the thing you </s><s>[INST] made. You made a few biological reproduce. [/INST] Yeah. I made biological entities. I mean, I came and my wife, let's face it, like I would love to say I made them, but the womb whipped them up. Um but it is the, yeah, it's the best. It's, I've never experienced anything like it before. It is the, as far as I'm concerned, the greatest thing that has ever happened to me. And, and that's why I was able to answer your question with like, hell yes chuck. Yes, That's great. I get to be around my kids again. I'll always be around my kids. Always be around my Children. That's incredible. That's the joy. So like, so for me. Mhm the part of myself that used to torture myself more specifically around like my mom dying feeling like I wasn't there enough for her wishing that I had spent more time with her wishing I'd spent more time with my dad wishing that like, you know, looking back at like how like I was just so desperately trying to evade the fact that she was dying uh and through and in that evasion successfully, like distanced myself from her and like in ways that I really wish I hadn't uh I'm just saying that cause it's one of my regrets, it's like a big have a lot of little regrets, but that's a big one. And so when you have kids, you look back at everything you did and you think like fuck if I'd gone left at that point instead of right, if I had eaten, who knows what if I had eaten like a turkey sandwich when my balls were creating the come that was going to make my kids, would I have a different kid, would this being not exist in my life? Like you start looking at everything and you realize like, thank God, thank God for every single thing that happened to me because it all led up to this and oh for me, that is the that's that it's like it frees you and this, it liberates you because you realize like, oh wow, it's clumsy and selfish and and and at times rotten if I've as I've been in my life that did not impede the universe at all from allowing this, these two beautiful beings to exist in the world. So </s><s>[INST] maybe all of it enabled all of it like a concert perfectly led up to that little beautiful moment. Is there ways you would like to be about a father? [/INST] Oh yeah, for sure. Absolutely. There's a, there's an actual, I read something in a book. It's called Good Enough the mantra for a parent Good Enough Because when you are in the presence of something you love more than you've ever experienced love you, you want to be perfect. Like you want to be, I can't, I gotta work man, I gotta go on the road. I've gotta work. I gotta support the family. So that means I have to work like I work, you know, you know what it's like having a podcast, you fucking workman and, and uh you know, it's a full time job because I've, you know, I do stand up to and all the other stuff. So I feel sometimes I feel like, oh my God, I want to spend more time with him. Like I should be spending more time with him. But then also I want to create, I want to work, I I like being the the provider. So that's something I feel guilty about. You know, </s>
<s>[INST] Well, that's an interesting, so ecology of practice. So like finding a place where a lot of people are doing different things that are interesting interplay with each other, but at the same time it's not a cult like, uh where ideas can flourish now. How the hell do you know? Um [/INST] because in </s><s>[INST] a place where people are really excited about doing stuff. [/INST] Yes, that's </s><s>[INST] very right for cult formation, [/INST] especially if they're a wash and a culture in which we have ever expanding waves of bullshit? Yes, precisely. So try </s><s>[INST] to keep away from the bullshit is the advice. [/INST] Yes, No, I mean I take this very seriously. And I was with a bunch of people in Vermont at the respond retreat, people rave kelly. Was there a bunch of people who have set up colleges of practices and created communities and I have good reason to find all of these people trustworthy. And so we gathered together to try and generate real deal logos, flow in distributed cognition, exercise the collective intelligence and try and address that problem. Both in terms of, you know, meta curriculum that we can offer emerging communities in terms of practices of vetting, how we will self govern the federation were forming so that we can resist glorification </s><s>[INST] glorification of people or ideas. [/INST] Both both </s><s>[INST] some of us just get unlucky, [/INST] some of us get unlucky and we all at respond we all had a tremendous sense of urgency around this but we were trying to balance it about not being premature. But there it was going to I mean there's we're going to produce a medical um that's coming in months. There's gonna be a scientific paper about integrating the scientific work on wisdom with this practitioner based ideas about the cultivation of wisdom. There's going to be uh projects about how we can create a self correcting vetted vetting system. So we can say to people, we think this ecology is legit, it's in good fellowship with all these other legit ecology is we don't know about that one. Were hesitant about that one. It's not in Good fellowship, we have concerns, here's why we have our concerns, etcetera. And you may say, well, who are you to do that? It's like nobody but somebody's gotta do it, right, and that's what it comes down to. And so we're gonna give it our best effort. It's </s><s>[INST] worth a try. You talked about the meaning crisis in uh human civilization, but in your own personal life, what has been a dark place you've ever gone in your mind? Has there been difficult times in your life where you really struggled? [/INST] So when I left fundamentalist Christianity for a while, I was just sort of hard bitten atheist. Um the problem with leaving the belief structure was that I didn't deal with all the non proposition all things that had gotten into me all the procedures and habits and all the perspectives and all the identities and the trauma associated with that. So, you know, I required therapy, required years of meditation and tai chi and I'm still wrestling with it. But for the first four or 5 years I would I I described it like this. It was I called it the black burning. I felt like there was a a blackness that was on fire inside of me precisely because the religion had left a taste for the transcendent in my mouth. But it had the food, it had given me food and square quotes had soured in my stomach and made me nauseous and the and the juxtaposition, The juxtaposition of those seemed like an irresolvable problem for me. That was a very, very dark time for me. </s><s>[INST] Did it feel lonely [/INST] when it was very bad? It felt extremely lonely and in the and deeply alienating the universe seemed absurd and there was also uh existential anxiety. I talk about these things for a reason. I don't just talk about them as things I'm pointing to, I'm talking about them as seeing in myself and people I care, you know, having undergone them and how how they can bring you close to, you know, self destructive. I started engaging in kinds of self destructive behavior. So </s><s>[INST] the meaning crisis to you is not just the thing you look outside and and see many people struggling you yourself a struggle. [/INST] But that's that's in fact the narrative is I struggled with it thinking it was a purely personal idiosyncratic thing. I started learning the cox, I started doing the tai chi in the meditation, I started doing all this right, Socratic philosophy. And when I started to talk about these pieces, I saw my students eyes light up and I realized, oh wait, maybe this isn't just something I'm going through talking to them and then doing the research and expanding it out. It's like, oh many people in a shared fashion and also in an individual lonely fashion are going through meaning crisis? </s><s>[INST] Well we talked a lot about wisdom and meaning and you said that the goal is to love wisely. So let me ask about Love, what's the role of love in the human condition? [/INST] I mean it's even central to, to, to, to reason and rationality, This is plato but Spinoza the most logical of the rationalist, you know, the ethics is written like euclid geometry, but he calls it the ethics for a reason </s><s>[INST] because [/INST] he wants to talk about the blessed life and what does he say? He says that ultimately reason needs love because love is what brings reason out of being entrapped in the gravity well of ego centrism and Murdoch, iris Murdoch said, I think really beautifully love is when you painfully realize that something other than yourself is real, </s>
<s>[INST] that we just don't know about um I mean there's it's endless if you had billions of dollars trillions of dollars. What would be the efforts in the Amazon for both conservation and for [/INST] exploration? Which are tied together. Yeah, exactly. First, arrest the deforestation, so we don't have an ecological crisis on our hands. We don't want to keep losing species, losing indigenous cultures, losing the climate stabilizing services that the Amazon provides </s><s>[INST] as a whole. Stop that. That's my first mission. Next, then we can play. Which are tied together. [/INST] And then it's like, let's go find... I've flown over the Amazon and assessed none. It's like, you see things where you go, we have to go see what that is. Weird lakes or shapes in the jungle </s><s>[INST] that don't make sense, that are strange. So even at that level, you can see weirdness. [/INST] You can see different signs of possible awesomeness. The jungle is so weird. And here's the other thing. The region I've been working in, you see where the researchers go. There's certain biological stations, there's certain places where like, oh, this university has a relationship with this. So everybody goes to the same few study sites, and then they walk on the same trails, and they have the same guides. When you fly in a Cessna, and you fly a few hours away from all that, and you see a tiny little tributary, and then you fly for 40 minutes over unbroken green, just wild, before you reach another tributary. Even if somebody could survive going up that tributary, had the expeditionary expertise, and the ability to survive getting shot at by arrows, if they could get up that tributary. Now, cut perpendicular into the jungle, which I don't do on the solos. You can't, you can never, don't ever leave the river. But you're telling me that in that span of 70 miles between tiny tributaries at the edge of the world, no one's been there. None of us have been there. Maybe somebody 10,000 years ago was there, but we don't know what populations of things are there. We don't know what ruins are there. And so there's so much undiscovered stuff in the Amazon that is </s><s>[INST] just waiting, just waiting. What is the process of exploring that? So how does money get converted [/INST] towards exploration? Is there safe ways of doing that? There's places where we found out about things that have to be explored, but where you come up with, well, how do we do this without getting shot? And not only without getting shot, but also without endangering them too. Because how stupid are we if we go in there to people that are living in the jungle, not bothering us, and we go and insert ourselves into there because we're curious about some rocks. And that doesn't seem fair for the loss of life. And so that's something that we're working on. And one thing, of course, is Lidar and stuff, but eventually at the end of everything, </s><s>[INST] it comes down to boots on the ground. As somebody who has to ask that very question about how to deal with uncontacted tribes that are going to kill you, but you also don't want to disturb their environment. If you were an intelligent alien civilization and you came about Earth, how would you interact with it? Can you put yourself in the mind of an alien civilization? Because there seems to be some parallels here. It is actually right. It's like a microcosm of- We're very aggressive. Human civilization is very aggressive. So if we were easily, we get threatened easily for stupid reasons. Because we start, American military probably thinks it's like the Chinese [/INST] or the Russians, if we see any kind of flying objects, it gets very on edge. It is actually right. I don't know. Part of it is like, you just want to ask, that's the thing, </s><s>[INST] I just want to ask questions. Yeah, but you don't know the same language. First of all, [/INST] you send a boat of bananas. You send a boat of bananas, you get shot. I mean, picture, if aliens landed in New York, how long would it take for one of them to get shot? </s><s>[INST] It'd be minutes. It'd be a matter of minutes. Yeah, that's because it's New York. Everywhere else. Look where we are right now. That's true. It'd be even worse here. Yeah. That makes me really wonder what is the right way to interact with intelligent life that's not like our own. I hope, I dream of in our lifetime, we would interact with possibly life on Mars or on one of the moons of Jupiter or Saturn. And how do you interact with that thing? There's very technical, biological, chemical processes, but also if there's any kind of intelligence, how do you try to communicate with that intelligence? [/INST] So we're not talking about a cockroach. We're talking about something that's clearly doing </s><s>[INST] things, making things. Or a cockroach, possibly. How do you know the difference between a cockroaches? How do you know we were just talking about developments? We don't know. We don't know. Just like a race of philosopher cockroaches just chilling on the rocks. Well, here on Earth, there seems to be a strong correlation between size and intelligence. It seems like the bigger things have bigger nervous systems and brains, [/INST] and so they're usually smarter. Well, that doesn't... I think it's brain, it's the ratio, brain to body, because you have crows that are up among the most intelligent, </s><s>[INST] and it's the size of the brain to the size of the body. But there also could be kinds of intelligence that we're not appreciating. Maybe cockroaches. They survived the longest. They're talking shit about us right now. It's dumb humans. They're like, dude, these rocks are so great. A couple of hundred years. Exactly. [/INST] These rocks are so great. Did you ever hear that Kurt Vonnegut, where the two space travelers get lost? This really impacted me as a kid, because my dad was an English teacher, so he's always quoting Dostoyevsky and Kurt Vonnegut. And these two space travelers get crash-landed in a cave, and on the walls of the cave are the harmoniums, and these kite-shaped animals, and they feed off the vibrations of the cave, and that's all they do. They don't hurt each other, they just do that. And so for like two years, these travelers are stuck and they're trying to fix their ship, and one of them starts playing music for the harmoniums. And the harmoniums love him for the music, and they all come around him, and he plays this music for him. And finally, they fix the ship. And the one guy is like, all right, let's get out of here. And the other guy is like, you know what, I'm staying. He goes, I found a place where I can do good. I'm not hurting anybody and they love me. </s>
<s>[INST] where I've described these places. That's so interesting. These places, however much detail you could describe them and you can place them on a sheet of paper through introspection, through this self-awareness that it comes all from this particular machine. That's exactly right. [/INST] Yeah, yeah. And I love that about being alive. Like, the fact that I'm not only experiencing the world, but I'm also experiencing how I'm experiencing the world. Sort of a lot of this introspection, </s><s>[INST] a lot of this self growth, a lot of this self growth. And I love this dance we're having, you know, the language models, at least GPT 3.5 and 4, seem to be able to do that too. Yeah, yeah. You seem to explore different kinds of things about what, you know, you could actually have a discussion with it, of the kind, why did you just say that? Yeah, exactly. And it starts to wonder, yeah, why did I just say that? [/INST] Yeah, you're right, I was wrong. Yeah, yeah. </s><s>[INST] And it starts to wonder, I was wrong, it was doesn't, and then there's this weird kind of losing yourself in the confusion of your mind, and it, of course, it might be anthropomorphizing, but there's a feeling like, almost of a melancholy feeling of like, oh, I don't have it all figured out. Almost like losing your, you're supposed to be a knowledgeable, a perfectly fact-based knowledgeable language model, [/INST] and yet you fall short. I was wrong, it was doesn't. So human self-cautiousness, in my view, may have a reason through building mental models of others. This whole fight or fright kind of thing, that basically says, I interpret this person as about to attack me, or, you know, I can trust this person, et cetera, and we constantly have to build models of other people's intentions, and that ability to encapsulate intent and to build a mental model of another entity is probably evolutionarily extremely advantageous, because then you can sort of have meaningful interactions, you can sort of avoid being killed and being taken advantage of, et cetera, and once you have the ability to make models of others, it might be a small evolutionary leap to start making models of yourself. So now you have a model for how that functions, and now you can kind of, as you grow, have some kind of introspection of, hmm, maybe that's the reason why I'm functioning the way that I'm functioning. And maybe what chat GPT is doing is, in order to be able to, again, predict the next word, it needs to have a model of the world. So it has created now a model of the world, and by having the ability to capture models of other entities, when you say, you know, say it in the tone of Shakespeare, or in the tone of Nietzsche, et cetera, you suddenly have the ability to now introspect and say, why did you say this? Oh, now I have a mental model of myself, </s><s>[INST] and I can actually make inferences about that. Well, what if we take a leap into the hard problem of consciousness, the so-called hard problem of consciousness? So it's not just sort of self-awareness. It's this weird fact, I want to say, that it feels like something to experience stuff. It really feels like something to experience stuff. There seems to be a self attached to the subjective experience. How important is that, how fundamental is that to the human experience? Is this just a little quirk and sort of the flip side of that? [/INST] Do you think AI systems can have some of that same magic? The scene that comes to mind is from the movie Memento, where it's this absolutely stunning movie where every black and white scene moves in the forward direction and every color scene moves in the backward direction. And they're sort of converging exactly at a moment where the whole movie's revealed. He describes the lack of memory as always remembering where you're heading, but never remembering where you just where. That's sort of this encapsulating the sort of forward scenes and back scenes. But in one of the scenes, the scene starts as he's running through a parking lot, and he's like, oh, I'm running, why am I running? And then he sees another person running beside him on the other line of cars. He's like, oh, I'm chasing this guy. And he turns to work with him, the guy shoots at him. He's like, oh no, he's chasing me. Okay. So in a way, I like to think of the brain as constantly playing these kinds of things where you're walking to the living room to pick something up and you're realizing that you have no idea what you wanted, but you know exactly where it was, but you can't find it. So you go back to doing what you were doing. Oh, of course, I was looking for this. And then you go back and you get it. And this whole concept of we're very often sort of partly aware of why we're doing things. And we can kind of run an autopilot for a bunch of stuff. And this whole concept of sort of making these stories for who we are and what our intents are. And again, sort of trying to pretend that we're kind of on top of things. </s><s>[INST] So it's a narrative generation procedure that we follow, but what about that, there's also just like a feeling. It doesn't feel like narrative generation. The narrative comes out of it, but then it feels like a piece of cake is delicious. [/INST] It feels delicious. It doesn't feel like narrative generation. It's good. There's two components to that. Basically for a lot of these cognitive tasks where we're kind of motion planning and path planning, et cetera, maybe that's the neocortical component. And then for, I don't know, intimate relationships for food, for sleep and rest, for exercise, for overcoming obstacles, for surviving a crash, or sort of pushing yourself to an extreme and sort of making it, I think a lot of these things are sort of deeper down and maybe not yet captured by these language models. And that's sort of what I'm trying to get at when I'm basically saying, listen, there's a few things that are missing. And there's like this whole embodied intelligence. It's called emotional intelligence. This whole sort of baggage of feelings </s>
<s>[INST] And that was his last book, it's actually his next [/INST] to last book. I don't know how you pulled this off, but he had one more after he died called Escape from Evil. And evidently it was supposed to originally the denial of death was supposed to be this giant 1000 page book that was both. And they split it up and the what became escape from evil. His wife Marie Becker finished well be that as it may in it is in the denial of death where Becker just says in the first paragraph, I believe that the terror of death and the way that human beings respond to it or decline to respond to it is primarily responsible for almost everything we do, whether we're aware of it or not. And mostly we're not. And so I read that first paragraph lex and I was like, wow, okay, this dude, </s><s>[INST] you're on to something, You're onto something, the same thing, It's the [/INST] same thing. And then it reminded me, I think, uh, not to play psychologist, but you know, let's face it. I believe there's a reason why we end up drifting where we ultimately come to. So I'm in my mid twenties, I got Ernest Becker's book in my hand and the next thing I know, I'm remembering when I'm eight years old, the day that my grandmother died. And you know, the day before my mom um said, oh, say goodbye to grandma, she's not well. And okay. So I was like, okay grandma, and I knew she wasn't well, but I didn't really appreciate the magnitude of her illness. Well, she dies the next day. Um, it's in the evening and I'm just sitting there looking at my stamp collection and I'm like, wow, I'm gonna miss my grandmother. And then I'm like, no, wait a minute. That means my mother is going to die and after she gets old and that's even worse after all, who's going to make me dinner? And that bothered me for a while. But then I'm looking at the stamps all the dead american presidents and I'm like, there's George Washington. He's dead. There's thomas jefferson, he's dead. My mom's gonna be dead. Oh, I'm going to get old and be dead someday. And at eight years old, that was my first explicit existential crisis. I remember it being, you know, one of these blood curdling realizations that I tried my best to ignore for the most of the time I was subsequently growing up. But fast forward back to Skidmore College Mid 20s Reading Becker's book in the 1980s, thinking to myself, wow, one of the reasons why I'm finding this so compelling is that it squares with my own personal experience. And then so make a short story long and I'll shut up lex. But </s><s>[INST] what what grabbed [/INST] me about back or, and this is in part because I read a lot of his other books, um, there's another book, The Birth and Death of meaning, which is framed um, in from an evolutionary perspective. And and then the denial of death is really more framed from an existential psychodynamic vantage point. And as a young academic, I was really taken by what I found to be a very potent juxtaposition that you really don't see that often. Yet usually evolutionary types are eager to dismiss the psychodynamic types and vice versa. And maybe only john Bowlby, you know, there's there's other folks. But, uh, the attachment theorist john Bowlby was really one of the first serious academics to say these, um, these ways of thinking about thanks are quite compatible. And can </s><s>[INST] you comment on what's what a psychodynamic view of the world is versus an evolutionary view of the world, just in case people are not. Yeah, [/INST] absolutely. That's that's a fine question. Well, for the evolutionary types um, in general are interested in how it is and why it is that Well, we have adapted to our surroundings in the service of persisting over time and being represented in the gene pool they're after. Used to be </s><s>[INST] a fish, we used to be a fish. And uh and I would end up talking on a podcast how we came to be that way, how we [/INST] came to be that way. And so, whereas the existential psychodynamic types, I would say are more interested in development across a single lifespan. And but but the evolutionary types dismissed the psychodynamic types as overly speculative and devoid of empirical support for their views. Uh they uh you know, uh they'll just say these guys are talking should if you'll pardon the expression. And of course you can turn right around and say the same about the evolutionary types that they are often and rightfully criticized evolutionary psychologists for what are called the just so stories where it's like, oh, this is probably why fill in the blank is potentially adaptive. And my thought again early on was I didn't see any um, intrinsic antithesis between these viewpoints, I just found them dialectic lee compatible and I'm very powerful when combined. </s>
<s>[INST] true. And uh you're now uh moved to Stafford. I'm gonna try not to say anything about how great it is. What's that movement, like what it's East Coast to west Coast [/INST] is great. M. I. T. Has been very good to me it continues to be very good. To me it's an amazing place. There's continue have so many amazing friends and colleagues there, I'm very fortunate to have been able to spend a lot of time at M. I. T. Stanford is also amazing and part of what attracted out here was not just the weather but also you know Silicon Valley, let's face it is really more of the epicenter of the technological revolution. And I want to be close to the people who are inventing Ai and elsewhere a lot of it is being invested M. I. T. For that matter in europe and china and elsewhere um India but um but being a little closer to some of the key technologists was something that was important to me and and uh you know it may be shallow but I also do enjoy the good weather and uh you know I felt a little ripped off when I came here a couple months ago and immediately there the fires and my eyes were burning, the sky was orange and there's the heat waves and you know, so it wasn't exactly what I've been promised but fingers crossed it'll it'll get back to a better </s><s>[INST] maybe on a brief aside there's been some criticism of academia and universities and different avenues and I as a person who's gotten to enjoy universities from the pure playground of ideas that it can be. I always kind of try to find the words to tell people that these are magical places. Is there something that you can speak to that is beautiful or powerful about universities. [/INST] Well sure I mean first off I mean economists have this concept called revealed preference. You can ask people what they say, We can watch what they do. And so obviously by revealed preferences. I love academia here. I could be doing lots of other things, but it's something I enjoy a lot. And I think the word magical is exactly right. At least it is for me. Uh I do what I love. You know, hopefully my dean won't be listening, but I would do this for free. You know, it's it's just what I like to do. I like to do research. I love to have conversations like this with you and with my students, with my fellow colleagues. I love being around the smartest people I can find and learning something from them and having them challenge me and um that just gives me, gives me joy. Um and every day I find something new and exciting to work on and university environment is really filled with other people who feel that way. And so I feel very fortunate to be part of it and I'm lucky and it's just that I'm in a society where I can actually get paid for it and put food on the table while doing the stuff that I really love and I hope someday everybody can have jobs that are are like that and I appreciate that it's not necessarily easy for everybody to have a job that they both love and also they get paid for. Um so there are things that don't go well in academia, but by and large, I think it's a kind of, you know, kinder gentler version of a lot of the world, you know, we sort of cut each other a little slack on things like uh you know, on just a lot of things. Um you know, of course there's harsh debates and discussions about things and some petty politics here and there, I personally try to stay away from most of that sort of politics is not my thing, and so it doesn't affect me most of the time, sometimes a little bit maybe. Um but um but you know, being able to pull together something, we have the Digital Economy lab, we get all these brilliant grad students and undergraduates and post talks that are just doing stuff that I learned from and every one of them has some aspect of what they're doing that's just, I couldn't even understand, It's like way, way more brilliant and it's that's really to me actually really enjoy that, being in a room with lots of other smart people and uh and stanford has made it very easy to attract, you know, those people um I just, you know, say I'm going to do a seminar, whatever the people come, they come and want to work with me. Um we get funding, we get data sets and it's come together real </s><s>[INST] nicely and the rest is just [/INST] fun, it's fun. Yeah, we feel like we're working on important problems, you know, and and we're doing things that, you know, I think our our First Order in terms of what's important in the world and that's very satisfying to me. </s><s>[INST] Maybe a bit of a fun question. What three books, technical fiction, philosophical, you've enjoyed had a big, big impact in your life? [/INST] Well, I guess I go back to like my teen years and uh you know, I read Siddhartha which is a philosophical book and kinda helps keep me keep me centered about Yeah, Herman has exactly, don't get too wrapped up in material things or other things and just sort of, you know, try to find peace on things. Um a book that actually influenced me a lot in terms of my career was called the Worldly philosophers by robert Heilbroner. It's actually about economists, it goes through a series of different companies written a very lively form and it probably sounds boring, but it did describe whether it's Adam smith or Karl Marx or john Maynard Keynes and each of them sort of what their key insights were, but also kind of their personalities and I think that's one of the reasons I became an economist was just understanding how they grappled with the big questions of the </s>
<s>[INST] Will also donate $10 to first an organization that is helping to advance robotics and stem education for young people around the world. And now here's my conversation with dan Carlin. Let's start with the highest philosophical question, do you think human beings are fundamentally good or are all of us capable of both good and evil and it's the environment that molds, how we, the trajectory that we take their life, [/INST] How do we define evil, evil seems to be a situational eye of the beholder kind of question. So if we define evil, maybe I can get a better idea of and, and and that could be a whole show couldn't defining evil. But when we say evil, what do we mean? </s><s>[INST] That's a slippery one. But I think there's some way in which your existence, your presence in the world leads to pain and suffering and destruction for many others in the rest of the world. So you you steal the resources and you use them to create more suffering than there was before in the world. So I suppose it's somehow deeply connected to this other slippery award was just suffering as you create suffering in the world. You bring suffering to the world. [/INST] But here's the problem. I think with it because I, I fully see where you're going with that and I understand it. The problem is, is the question of the reason for inflicting suffering. So sometimes one might inflict suffering upon one group of individuals in order to maximize a lack of suffering with another group of individual or one who might not be considered evil at all, might make the rational, seemingly rational choice of inflicting pain and suffering on a smaller group of people in order to maximize the opposite of that for a larger group of </s><s>[INST] people. Yeah, that's one of the dark things about, I've spoken and read the work of Stephen Kotkin, I'm not sure if you're familiar with the historian and he's basically a Stalin, uh joseph Stalin scholar. And one of the things I realized, I'm not sure where to put Hitler, but with Stalin, it really seems that he was sane and he thought he was doing good for the world. I really believe from everything I've read about Stalin that he believed that communism is good for the world. And if you have to kill a few people along the way, it's like you said, the small groups, if you have to sort of remove the people that stand in the way of this utopian system of communism, then that's actually good for the world. And it didn't seem to me that he could even consider the possibility that he was evil. He really thought he was doing good for the world. And that's stuck with me because he's one of the most is to our definition of evil. He seems to have brought more evil onto this world than almost any human in history and I don't know what to do with that. [/INST] Well, I'm fascinated with the concept, so fascinated by it that the very first hardcore history show we ever did, which was a full 15 or 16 minutes um was called alexander versus Hitler and the entire question about it was the motivations, right? So if you go to a court of law because you killed somebody, One of the things they're going to consider is why did you kill them, right? And if you killed somebody, for example, in self defense, you're going to be treated differently than if you maliciously killed somebody maliciously to take their wallet, right? And in the show, we we wondered because, you know, I don't really make pronouncements, but we wondered about, uh, if you believe Hitler's writings, for example, Minkoff, which, you know, is written by a guy who's a political figure who wants to get off. So, I mean, it's about as believable as any other political tract would be, but in his mind, the things that he said that he had to do were designed to for the betterment of the german people, right? Whereas alexander the Great, Once again, this is somebody from more than 2000 years ago. So with lots of propaganda in the intervening years. But one of the views of alexander the Great, is that the reason he did what he did was to, for lack of a better word, write his name in a more permanent graffiti on the pages of history, right? In other words, to glorify himself. And if that's the case, does that make alexander a worst person, that Hitler, because Hitler thought he was doing good. Whereas alexander, if you believe the interpretation was simply trying to exalt alexander. So, the motivations of the people doing these things, it seems to me matter, um I don't think you can just sit there and go, the only thing that matters is the end result because that might have been an unintentional byproduct, in which case that person had, you been able to show them the future might have changed what they were doing. So were the evil or misguided or wrong or made, you know, so, and I hate to do that because there's certain people like Hitler that I don't feel deserve the benefit of the doubt at the same time, if you're fascinated by the concept of evil and you delve into it deeply enough, you're going to want to understand why these evil people did what they did. And sometimes it can confuse the hell out of you, You know, who wants to sit there and try to see things from Hitler's point of view to get a better understanding and, and sort of commiserated with. So. Um, but I'm obviously first history show, I'm fascinated with the concept. </s><s>[INST] So do you think it's possible if we put ourselves in the mindset of some of the people that have led created so much suffering in the world that all of them had their motivations were had good intentions underlying them? [/INST] No, I don't, I mean, it's simply because there's so many, I mean the law of averages would would suggest that that's not </s><s>[INST] true. I guess it is pure evil possible, meaning you are, again, it's slippery, but you, the suffering is the goal, [/INST] suffering, intentional suffering. Yes, I think that, and I think that there's historical figures that that that one could point. And but that gets to the deeper question of are these people saying, do they have something wrong with them? Are they twisted from something in their youth? Um, you know, I mean, these are the kinds of things where you start to delve into the psychological makeup of these people. In other words, is anybody born evil? And I actually believe that some people are, I think the D. N. A. Can get scrambled up in ways. I think the question of evil is important too, because I think it's an eye of the beholder thing. I mean, if Hitler for example had been successful and we were today on the sixth or seventh leader of the third Reich, since I think his entire history would be viewed through a different lens, because that's the way we do things, right. Um, Jenkins con looks different to the Mongolians than he does to the residents of Baghdad. Right. Um, and I think so, so, and I have the beholder question I think comes into all these sorts of things. As you said, it's a very slippery question. </s><s>[INST] Where do you put as somebody who is fascinated by military history, where do you put violence as uh, as in terms of the human condition is a core to being human? Or is it just a little tool that we use every once in a while. [/INST] So I'm going to respond to your question with a question. What do you see the difference being between violence and force? Let me go farther. I'm not sure that violence is something that we have to put up with as human beings forever, that we must resign ourselves to violence forever. But I have a much harder time seeing us able to abolish force and I there's going to be some ground where if those two things are not the same and I don't know that maybe they are, where there's certainly some crossover and the reason why I think force, you know, you're an engineer, you'll understand this better than I do, but think about it as a physical law. Um if you can't stop something from moving in a certain direction without pushing back in that same direction, um I'm not I'm not sure that you can have a society or civilization without the ability to use a counterforce when things are going wrong, whether it's on an individual level, right? Person attacks another person. So you step in to save that person um or on uh you know, even at the highest levels of politics or anything else, a counter force to stop the inertia or the impetus of of of another movement. So, I think that force is is a simple, almost law of physics in human interaction, especially at the civilisational level, I think civilization requires a certain amount of if not violence than force. So um and again, they talked, I mean it goes back into ST Augustine, all kinds of christian beliefs about the proper use of force and people have philosophically tried to decide between can you have a sort of an ahi NSA buddhist sort of, we you know, we would be non violent toward everything and exert no force or or there's a reason to have force in order to create the space for good. I think force is inevitable now we can talk and I have not come up to the conclusion myself, if there is a distinction to be made between force and violence, I mean this is um is a non violent force enough or is violence when done for the cause of good, a different thing than violence done either for the cause of evil as you would say, or simply for random reasons? I mean we humans lack control sometimes we can be violent for no apparent reason or goal. Um and that's, I mean you look at the criminal justice system alone in the way we we interact with people who are acting out in ways that we as a society have decided is intolerable. Can you deal with that without force? And at some level violence? I don't know, can you maintain Peacefulness without force? I don't know, </s><s>[INST] just to uh be a little bit more specific about the idea of force. Do you put force as general enough to include force in the space of ideas. So you mentioned buddhism or religion or just twitter? [/INST] I can think of no things farther apart than that. Okay. </s><s>[INST] Is uh the battles we do in the space of ideas of uh you know, the great debates throughout history. Do you put force into that? Or do you in this conversation? Are we trying to right now keep it to just physical force in saying that you you have an intuition that force might be with us much longer than violence? [/INST] I think the to bleed together. So, um take Because it's it's always it's always my go to example, I'm afraid, and I'm sure that the listeners all hate it, but but take take Germany during the 1920s, early 1930s, before the Nazis came to power. Uh and they were always involved in some level of force, you know, beating up in the streets or whatever it might be. But think about it more like an intellectual discussion until a certain point? Um, is that it would be difficult, I imagine, to keep the intellectual counterforce of ideas from at some point degenerating into something that's more um coercion, um, counterforce if we want to use the phrases we were just talking about. So, I think the two are intimately connected. I mean, actions follow thought right, and at a certain point, I think especially when when one is not achieving the goals that they want to achieve through a peaceful discussion or argumentation or trying to convince the other side that sometimes the next level of operations is something a little bit more physically imposing, if that makes sense? We go from the intellectual to the physical. </s><s>[INST] Yeah. So it too easily spills over into violence and one leads to the other often. So you kind of imply to perhaps a hopeful message. But let me ask you in the form of a question, do you think we'll always have war? [/INST] I think it goes to the fourth question to. So for example, um, what do you do? I mean, we're let's let's play with Nation States now, although I don't know that Nation States are something we should think of as a permanent constitution forever. Um, but how is one Nation states supposed to prevent another Nation state from acting in ways that it would see is either detrimental to the global community or detrimental to the interests of their own nation state? Um, you know, and I think I think we've had this question of going back to ancient times, but certainly in the 20th century, this has come up quite a bit. I mean, the whole Second World War argument sometimes revolves around the idea of what the proper counterforce should be. Can you create an entity, a league of Nations? The United Nations, a one world entity, maybe even that that alleviates the need for counterforce involving mass violence and armies and navies and those things. I think that's an open discussion, we're still having, </s><s>[INST] it's good to think through that because having us like a united nations, there's usually a centralized control. So there's humans at the top, there's committees and uh, usually like leaders emerge a singular figures that then can become corrupted by power. And it's just a really important. It feels like a really important thought experiment and something to really rigorously think through how can you construct systems of government that are stable enough to push us towards less and less war and less and less on stable? And another tough word, which is unfair of application of force? You know, as that's really at the core of the question that we're trying to figure out as humans as our weapons get better and better and better destroying ourselves. It feels like it's important to think about how we minimize the over application or unfair application of force. [/INST] There's other elements that come into play to you and I are discussing this at the very high intellectual level of things, but there's also a tail wagging the dog element to this. So think of the society of warriors, a tribal society from a long time ago. Um, how much do the fact that you have warriors in your society and that their reason for existing, what they take pride in what they train for, um, what their status in their own civilization. How much does that itself drive the responses of that society, right. Um, how much do you need war to legitimize warriors? Um, you know, that's the old argument that you get to and had this in the 20th century to that the creation of arms and armies creates an incentive to use them, right? And and that they themselves can drive that incentive as as a justification for their reasons for existence. You know? Um, that's where we start to talk about the interactivity of all these different elements of society upon one another. So when we talk about, you know, governments and war, well, you need to take into account the various things those governments have put into place in terms of systems and armies and things like that to protect themselves, right? For reasons we can all understand, but they exert a force on your range of choices, don't they? </s><s>[INST] It's true, you're making me realize that, uh, in my upbringing and I think I'm bringing of many warriors or heroes, you know, to me, I don't know where that feeling comes from, but to sort of die fighting is, uh, it's an honorable way to die. It feels like that [/INST] I've always had a problem with this because as a person interested in military history, the distinction is important. Um, and I try to make it at different levels. So at base level, the people who are out there on the front lines doing the fighting, uh, to me, those people can be compared with police officers and firemen and people that fire persons. Um, but but I mean, people that are involved in an ethical attempt to perform a task, which ultimately one can see in many situations as being a saving sort of task, right? Or or if nothing else, a self sacrifice for what they see as the greater good. Now, I draw a distinction between the individuals and the entity that they are part of a military. And I certainly draw a distinction between the military and then the entire, for lack of a better word, military industrial complex, that that service is a part of. Uh, I feel a lot less um moral attachment to uh, to those upper echelons than I do the people on the ground. The people on the ground could be any of us and have been in a lot of, you know, we have a very professional uh, sort of military now where it's a very uh, a subset of the population, but in other periods of time we've had conscription and drafts and and it hasn't been a subset of the population. It's been the population, right? And so it is the society oftentimes going to war, and I make a distinction between those warriors and the entities either in the system that they are part of the military or the people that control the military at the highest political levels. I feel a lot less moral attachment to them. And I have a much harsher about how I feel about them. I do not consider, uh, the military itself to be heroic and I do not consider the military industrial complex to be heroic, I do think that is a tail wagging the dog situation. I do think that draws us into looking at um, military endeavors as a solution to the problem much more quickly than we otherwise might. And to be honest, to tie it all together, I actually look at the, at the victims of this as these soldiers we were talking about. I mean, if you, if you set a fire to send firemen into to fight, </s><s>[INST] um, [/INST] then I feel bad for the firemen. I feel like you've abused the trust that you give those people right? So when, when people talk about war, I always think that the people that we have to make sure that a war is really necessary, uh, in order to protect are the people that you're going to send over there to fight that the greatest victims in our society of war are often the warriors. So I, in my mind, um, you know, when we see these people coming home from places like Iraq, a place where I would have made the argument and did at the time that we didn't belong to me, those people are victims. And I know they don't like to think about themselves that way because it runs totally counter to the ethos. But if you're sending people to protect this country's shore's, those are heroes. If you're sending people to go do something that they otherwise probably don't need to do. But they're there for political reasons or anything else you want to put in that's not defense related. Well then you've made victims of our heroes. And so I I feel like we do a lot of talk about our troops and our soldiers and stuff, but we don't treat them as valuable as we, as the rhetoric makes them sound. Otherwise we would be more, we would be much more careful about where we put them. If you're going to send my son and I don't have a son, I have daughters, but you're going to send my son into harm's way. I'm going to demand that you really need to be sending him into harm's way. And I'm going to be angry at you if you put him into harm's way, if he doesn't, if it doesn't warrant it. And so I have much more suspicion about the system that sends these people into these situations where they're required to be heroic, then I did the people on the ground that I look at as, um, either the people that are defending us, you know, in situations like this, you know, the Second World War, for example, or, or the people that, um, turn out to be the individual victims of a system where there's just a cog in the machine and the machine doesn't really care as much about them as as the rhetoric and the propaganda would insinuate. </s><s>[INST] Yeah. And uh, as my own family history, it would be nice if we can talk about. There's a gray area in, in the places that you're talking about. [/INST] It's a gray area in everything, </s><s>[INST] everything. But when that gray area is part of your own blood as it is for me, it's it's worth shining a light on somehow. [/INST] Sure, give me example what you mean. </s><s>[INST] So you did a program of four episodes of Ghosts of the Ost Front. So I was born in the soviet Union. I was raised in Moscow. My dad was born and raised in Kiev. My grandmother who just recently passed away was uh raised in Ukraine. She, it's a small city on the border between Russia and Ukraine. I have a [/INST] grandfather born in Kiev in </s><s>[INST] Kiev. The interesting thing about the timing of everything as you might be able to connect as she survived. She's the most badass woman I've ever encountered in my life and most of the warrior spirit I carry is probably from her. She survived polymer more the Ukrainian starvation of the 30s. She was a beautiful teenage girl during the Nazi occupation of so she survived all of that and of course family that everybody, you know, and so many people died the whole process. So, and one of the things you talk about in your program is that the gray area is even with the warriors, it happened to them just because you're saying now they didn't have a choice. So my my grandfather on the, on the other side, he was a machine gunner. Uh, that was in Ukraine, that that in the red army in the red Army and they threw uh like the statement was that there's, I don't know if it's obvious or not, but the rule was there's no surrender. So you you better die. So you I mean, you're basically, the goal was when he was fighting and he was lucky enough one of the only to survive by being wounded early on is there was a march of nazis towards against Moscow. And the whole goal in Ukraine was too slow every to slow them into the, into the winter. I mean, I view them as such a hero and he believed that he's indestructible, which is survivor bias and that, you know, bullets can't hurt him and that's what everybody believed. And of course, basically everyone that uh he quickly rose through the ranks. Let's just put it this way because everybody died. It was just bodies dragging these heavy machine guns, like always, you know, I was slowly retreating, shooting and retreating, shooting and retreating. And I don't know he was a hero to me. Like I always, I grew up thinking that he was the one that sort of defeated the Nazis, right? And but the reality that there could be another perspective, which is all of this happened to him by the incompetence of Stalin the incompetence, incompetence and uh men of uh the soviet Union being used like ponds in a in a ship really played game of chess. Right? So like one narrative as him as a victim as you're kind of describing. And it then somehow that's more paralyzing and that's more, yeah, I don't know. It feels better to think of him as a hero and as Russia, soviet union is saving the world. I mean, that narrative also is in the United States that that uh United States was key in saving the world from the nazis. It feels like that narrative is powerful for people. I'm not sure and I carry it still with me. But when I think about the right way to think about that war, I'm not sure if that's the correct narrative. [/INST] Let me suggest something. There's a line that that a marine named Eugene Sledge had said once. And I keep it on my phone because it's it's it makes a real distinction. And he said the front line is really where the war is and anybody even 100 yards behind the front line doesn't know what it's really like. Now. The difference is is there are lots of people miles behind the front line that are in danger, right? You can be in a medical unit in the rear and artillery could strike you planes because you could be in danger. But at the front line there are two different things. One is um that that at least. And I'm doing a lot of reading on this right now and reading a lot of veterans accounts, James jones who wrote Books like from here to eternity, fictional accounts of the Second World War, but he based them on his own service. He was at Guadalcanal for example, in 1942 and Jones had said that the evolution of a soldier in front line action requires an almost surrendering to the idea that you're going to live. You become accustomed to the idea that you're going to die. And he said, you're a different person simply for considering that thought seriously because most of us don't. But what that allows you to do is to do that job at the front line, right? If you're too concerned about your own life, Um you become less of a good guy at your job, right? The other thing that the people in the one in the 100 yards of the front line do that. The people in the rear medical unit really don't as you kill and you kill a lot, right? You don't just, oh, there's a sniper back here. So I shot him if we go from one position to another and we kill lots of people, Those things will change you and what that tends to do not universally because I've read accounts from Red Army soldiers and they're very patriotic, right? But a lot of that patriotism comes through years later as part of the nostalgia. And the remembering when you're down at that front 100 yards, it is often boiled down to a very small world. So your grandfather was your grandfather that the machine gun, he's concerned about his position and his comrades and the people who he owes a responsibility to. And it's a very small world at that point. And to me that's where the heroism is, right? He's not fighting for some giant world civilisational thing. He's fighting to save the people next to him and his own life at the same time because they're saving him too. And and that there is a huge amount of heroism to that. And that gets to our question about force earlier, why would you use force? Well, how bout to protect these people on either side of me right there lives um now is their hatred? Yeah, I hated the Germans for what they were doing. As a matter fact. I uh I got a note from a pole not that long ago and I have this tendency to refer to the nazis, right? The regime that was and he said, why do you keep calling them nazis? He says say say what they were they were Germans. And this guy wanted me to not absolve Germany by saying, oh it was this awful group of people that took over your country. He said, the Germans did this and there's that bitterness where he says, let's not forget, you know what they did to us and why and what we had to do back. Right. Um, so for me, when we talk about these combat situations, the reason I call these people heroic is because of they're fighting to defend things. We could all understand me if you come after my brother and I take a machine gun and shoot you. Um, and you're going to overrun me. I mean, you're gonna that becomes a situation where we talked about Counterforce earlier, um much easier to call yourself a hero when you're saving people or you're saving this town right behind you. And you know, if they get through your machine gun, they're going to burn these villages, they're gonna throw these people out in the middle of winter. These families, that to me is a very different sort of heroism than this Amorphous idea of patriotism. Patriotism is a thing that we often get um used with right people. People manipulate us through love of country and all this because they understand that this is something we feel very strongly, but they use it against us sometimes in order to whip up a war fever or to get people, I mean, there's a great line and I wish I could remember it in its entirety, determined during had said about how easy it was to get the people into a war. He says, you know, you just appeal to their patriotism. I mean there's buttons that you can push and they take advantage of things like love of country and the way we, the way we have a loyalty and admiration to the warriors who put their lives on the line, these are manipulate herbal things in the human species that reliably can be counted on to move us in directions that in a more um sober, reflective state of mind, we would consider differently. It gets the mean, you get this war fever up and people, people wave flags and they start denouncing the enemy and they start signing, you know, we've seen it over and over and over again in ancient times this happened. </s><s>[INST] But the love of country is also beautiful. So I haven't seen in America as much. So people in America love their country like this patriotism, strong in America, but it's not as strong as I remember. Even with my sort of being younger, the love of the soviet union [/INST] now, was it the soviet union? This requires a distinction Or was it mother Russia? </s><s>[INST] What it really was was the Communist Party. Okay, so it was it was a system in place, the system in place like loving. I haven't quite deeply psychoanalyzed exactly what you love. I think you love the that like populist message of the worker of the common man. So [/INST] let me let me draw the comparison then. Um and I often say this that that the United States, like the soviet union is an ideological based society, right? So you take a country like France, it doesn't matter which french government you're in now, the friendship in the french for a long time, right? Uh it's not based on an ideology, right? Whereas what unites the United States is an ideology freedom, liberty, the constitution, this is what draws, you know, it's the e pluribus unum kind of the idea right there, That out of many one. Well, what what binds all these unique, different people, the shared beliefs, this ideology, the soviet union was the same way because as, you know, the soviet union Russia was merely one part of the soviet union, and if you believe the rhetoric until Stalin's time, everybody was going to be united under this ideological banner someday, it it was was a global revolution. Um so ideological societies are different and to be a fan of the ideological framework and goal, I mean, I'm a liberty person, right? I would like to see everybody in the world have my system of government, which is part of a of a bias, right? Because they might not want that, but I think it's better for everyone because I think it's better for me at the same time when the ideology, if you consider and, you know, this stems from ideas of the enlightenment and there's a bias there. So my bias or toward the but you feel and this is why you say we're going to bring freedom to Iraq, we're gonna bring freedom to here, we're gonna bring freedom because we think we're spreading to use something that is just undeniably positive, we're going to free you and give you this. Um it's hard for me to wipe my own bias away from there, right? Because if I were in Iraq for example, I would want freedom, right? But if you then leave and let the Iraqis vote for whomever they want, are they going to vote for somebody that will, I mean, you know, you look at Russia now and I hear from Russians quite a bit because so much of my um my views on Russia and the soviet union were formed in my formative years and and you know, we were not hearing from many people in the soviet union back then, but now you do you hear from Russians today who will say your views on Stalin or archaic and cold. So so you try to reorient your beliefs a little bit. But it goes to this idea of if you gave the people in Russia a free and fair vote, will they vote for somebody who promises them a free and open society based on enlightenment democratic principles, or will they vote for somebody, we in the U. S. Would go what are they doing? They're voting for some strong man who's just you know, so um I think it's very hard to throw away our own biases and preconceptions and and you know it's an all eye of the beholder kind of thing. But when you're talking about ideological societies it is very different, difficult to throw off all the years of indoctrination into the superiority of your system. I mean listen in the soviet union Marxism one way or another was part of every classrooms, you could be studying geometry and they'll throw Marxism in there somehow because that's what united the society and that's what gave it a higher purpose and that's what made it in the minds of the people who were its defenders a superior morally superior system. And we do the same thing here. In fact most people do. But see you're still french no matter what the ideology or the government might be. So in that sense it's funny that there would be a Cold war with these two systems because they're both ideologically based systems involving peoples of many different backgrounds who are united under the umbrella of the ideology. </s><s>[INST] First of all that's brilliantly put, I'm in a funny position that uh in my formative years. So I came here when I was 13 is when I you know teenage is your first love or whatever as I fall in love, I fell in love with the american set of ideas of freedom and individuals. [/INST] Yes but </s><s>[INST] I also remember it's like you remember like maybe an ex girlfriend or something like that. I also remember loving as a very different human the the soviet idea like we had the national anthem which is still the, I think the most badass national anthem which is the soviet union, like saying we're the indestructible nation. I mean just the words are so like americans words are like, oh we're nice, like what we're freedom. But like a Russian soviet union national anthem was like we're bad motherfucker's, nobody will destroy us. I just remember feeling pride in a nation as a kid, like dumb not knowing anything because we all had to recite the stuff. It was, there's a uniformity to everything, There is pride underlying everything. I didn't think about all the destructive nature of The bureaucracy, the incompetence of you know, all the things that come with the implementation of communism, especially around the 80s and 90s. But I remember what it's like to love the that set of ideas. So in a funny place of like remember like switching the love because I'm you know, I kind of joke around about being Russian but you know, my my long term monogamous relationship is not with the idea of the american ideal. Like I'm stuck with it in my mind but I remember what it was like uh to love it and I think about that too when people criticize china or they criticize the current state of affairs with how Stalin is remembered and how Putin is to know that the you can't always wear the american ideal of individualism, radical individualism and freedom in analyzing the ways of the world elsewhere, like in china and Russia, that it does. If you don't take yourself too seriously as americans all do as I do. It's kind of a beautiful love to have for your government to believe in the nation to let go of yourself and your rights and your freedoms to believe in something bigger than yourself. That's actually uh that's a kind of freedom. That's you're actually liberating yourself. If you think like life is suffering, you're you're giving into the flow of the water, the flow the way of the world by giving away more power from yourself and giving it to what you would conceive as as the power of the people together together. We'll do great things and really believing in the ideals of what in that case, in this case, I don't even know what you would call Russia, but whatever the heck that is authoritarian, powerful state, powerful leader, believing that can be as beautiful as believing the american ideal. [/INST] Not just that, let me add to what you're saying and I'm very, I spend a lot of time trying to get out of my own biases. Uh It is, it is a fruitless endeavor long term, but you try to be better than you normally are one of the critiques that china and I always as an american, I tend to think about this as their government, right? This is a rationale that their government puts forward. But what you just said, you know, is actually if you can make that viewpoint beautiful is kind of a beautiful way of approaching it. The chinese would say that what we call human rights in the United States and what we consider to be everybody's birthright around the world is instead Western rights. That's the words they use Western rights. It's a it's a fundamentally Western oriented and I'll go back to the enlightenment, enlightenment based ideas um on what constitutes the rights of man. And they would suggest that that's not internationally and always applicable, right, that you can make a case. And again, I don't believe this if this runs against my own personal views, but that you could make a case that the collective well being of a very large group of people outweighs the individual needs of any single person, especially if those things are in conflict with each other, right? If you cannot provide for the greater good because everyone's so individualistic. Well then really what is the better thing to do right to suppress individualism? So everybody is better off? Um I think trying to recognize how someone else might see that is important if we want to. You know, you have talked about eliminating war. We talked about eliminating conflict. The first need to do that is to try to understand how someone else might view something differently than yourself. Um I'm famously one of those people who buys in to the ideas of, of traditional Americanism, right? And look what a lot of people who lived today. I mean they would seem to think that things like patriotism requires a belief in the strong military and all these things we have today, but that is a corruption of traditional Americanism, which viewed all those things with suspicion in the 1st 100 years of the republic, because they saw it as an enemy to the very things that americans celebrated right? How could you have freedom and liberty and individualistic expression if you had an overriding military that was always fighting wars and and and the founders of this country looked to other examples like europe for example and saw that standing militaries for example, standing armies were the enemy of liberty. Well, we have a standing army now. Um and and and one that is totally interwoven in our entire society. If you could, if you could go back in time and talk to john Quincy Adams, writerly President of the United States and show him what we have now, he would think it was awful and horrible and that somewhere along the line, the americans had lost their way and forgotten what they were all about. But we have so successfully interwoven This modern military industrial complex with the, the traditional uh benefits of the American system and ideology so that they become intertwined in our thinking. Whereas 150 years ago, they were actually considered to be at opposite polarities and a threat to one another. Um, so when you talk about the love of the nation, I tend to be suspicious of those things. I tend to be suspicious of government, I tend to tend to try very hard to not be manipulated. And I feel like A large part of what they do is manipulation and propaganda. And so, um I think a healthy skepticism of the nation state is actually 100% Americanism in the traditional sense of the word, but I also have to recognize as you so eloquently stated Americanism is not necessarily universal at all. And so I think we have to try to be more understanding cr the traditional american viewpoint is that if a place like china does not allow their people individual human rights, then they're being denied something, they're being denied. And 100 years ago they would have said their God given rights, man is born free. And if he's not free, it's because of something done to him, right? The government has taken away his God given rights. </s><s>[INST] I'm getting excited just listening to [/INST] that. But I mean, but I mean, I think, I think the idea that this is universal is in and of itself a bias now do I want freedom for everybody else. I sure do. But the people in the soviet union who really bought into that wanted the workers of the world to unite and not be exploited by, you know, the greedy, blood sucking people who worked them to death and pocketed all of the fruits of their labor. If you frame it that way, that sounds like justice as well, you know? So it is an eye of the beholder sort of thing. </s><s>[INST] I'd love to talk to you about Vladimir Putin sort of while we're in this feeling and wave of empathy and trying to understand others that are not like us. Yeah. One of the reasons I started this podcast is because I believe that there's a few people I could talk to some of it is ego, some of it stupidity. Is there some people I could talk to that? Not many others can talk to. The one person I was always thinking about was Vladimir Putin. Do you still speak the language? I speak the language very well. That makes [/INST] it even easier. I mean you might be you might be appointed for that job. </s><s>[INST] That's the context in which I'm asking you this question. What are your thoughts about Vladimir Putin from historical context? Have you studied him? Have you thought about him? [/INST] Yes. Uh studied as a, as a loaded word. Um here's here's and again I find it hard sometimes to not filter things through an american lens. So as an american, I would say that the Russians should be allowed to have any leader that they want to have. But what an american would say is, but there should be elections, right? So if the Russians choose Vladimir Putin and they keep choosing him, that's their business. Where as an american, I would have a problem is when that leader stops letting the Russians make that decision and we would say, well now you're no longer ruling by the consent of the governed, you've become the equivalent of a person who may be oppressing your people. You might as well be a dictator right now, there's a difference between a freely elected and re elected and re elected and re elected dictator, right? If that's what they want. And and look, i it would be silly to broad brush the Russians like it would be silly to broad brush anyone right? Millions and millions of people with different opinions amongst them all, but they seem to like a strong person at the helm. And listen, there's a giant chunk of americans who due to um in their own country. But an american would say as long as the freedom of choice is given to the Russians to decide this and not taken away from the right, it's one thing to say, he was freely elected, but a long time ago and we've done away with elections since then is a different story too. So my attitude on on Vladimir Putin is if that's who the Russian people want and you give them the choice right? If he's only there because they keep electing him. That's a very different story when when he stops offering them the option of choosing him or not choosing him. That's when it begins to look nefarious to someone born and raised with the mindset and the ideology that is an integral part of of yours, truly and that I can't, you know, you can see gray areas and nuance all you like, but it's hard to escape as you wish. And you you alluded to this too. It's hard to escape what was indoctrinated into your bones in your formative years. Uh it's like your bones are growing right and you can't go back. So to me this is so much a part of who I am that I have a hard time jettisoning that and saying, oh no, Vladimir Putin not being elected anymore. It's just fine. I'm too much of a product of my upbringing to go there. Does that make sense? </s><s>[INST] Yeah, absolutely. But of course there's like we were saying these gray areas, which is I believe I have to think through this, but I think there is a point of which Adolf Hitler became the popular choice in Nazi Germany in the 30s. There is a, in the same way from an american perspective you can start to criticize some in a shallow way, some in a deep way, the way that Putin has maintained power is by controlling the press. So limiting one other freedom that we americans value, which is the freedom of the press or freedom of speech that he it is very possible now things are changing now, but for most of his presidency, he was the popular choice. And sometimes by far and you know I have actually don't have real family in Russia who don't love Putin. The only people who write to me about Putin and not liking him are like sort of activists who are young, right. But like to me they're strangers. I don't know anything about them. People I do know and have a big family in Russia. They love Putin. [/INST] They do, they miss elections, would they want the choice to prove it at the ballot box? And and or or are they so in love with him that they wouldn't want to take a chance that someone might vote him out. </s><s>[INST] No, they don't think of it this way and they are aware of the incredible bureaucracy and corruption that is lurking in the shadows, which is true in Russia [/INST] everywhere </s><s>[INST] everywhere. But like there's something about the Russian, it's the remnants, it's corruption is so deeply part of the Russians. So the soviet system that even the overthrow of the soviet, the breaking apart of the soviet union and uh Putin coming and reforming a lot of the system. It's still deeply in there and and they're aware of that that's part of the like the love for Putin is partially grounded in the fear of what happens when the corrupt takeover, the greedy take over. And they they see Putin as the stabilizer is like hard like force that says [/INST] counterforce counterforce that get your </s><s>[INST] ship together. Like basically from the western perspective, Putin is terrible, but from from the Russian perspective, Putin is the only thing holding this thing together before ghosts if it collapses. Now, the from the Garry Kasparov has been loud on this. You know, a lot of people from the Western perspective say, well if it has to collapse, let it collapse, you know, that's easier said than done when you don't have to live through that. Exactly. And so anyone worrying about their family about and they also remember the The inflation and the economic instability and the suffering and the starvation that happened in the 90s with the collapse of the Soviet Union and they saw the kind of reform in the economic vibrancy that happened when Putin took power that they think like this guy is holding it together and they see elections as potentially being mechanisms by which the corrupt people can manipulate the system unfairly as opposed to letting the people speak with their voice. They somehow figure out a way to uh manipulate the elections to elect somebody uh like one of them Western revolutionaries. And so I think one of the beliefs that's important to the american system is the belief in the electoral system, that the voice of the people can be heard in the various systems of government, whether it's judicial, whether it's, uh, I mean, basically the assumption is that the system works well enough for you to be able to uh elect the popular choice. [/INST] Okay, so there's a couple of things that come to mind on that. The first one has to do with the idea of oligarchs. Um, there's a belief in political science, uh, you know, it's not the, the overall believe, but but that every society is sort of an oligarchy, really, if you break it down. Right? So what you're talking about are some of the people who would form an oligarchic class in Russia. And that Putin is the guy who can harness the power of the state to keep those people in check. The problem, of course, in a system like that, a strongman system, right? Where you have somebody who can, who can hold the reins and steer the ship when the ship is violently in a storm, is the succession. So if you're not creating a system that can operate without you, then that terrible instability and that terrible future that you that you justify the strongman for is just awaiting your future, right? I mean, unless unless he is actively building the system that will outlive him and allow successors to do what he's doing, then what you've done here is create a temporary, I would think a temporary stability here, because it's the same problem you have in a monarchy. Right? Um where where you have this one king and he's particularly good or you think he's particularly good, but he's going to turn that job over to somebody else down the road. And the system doesn't guarantee because no one's really worked on. And again, you would tell me if if Putin is putting into place, I know he's talked about it over the years putting into place a system that can outlive him and that will create the stability that the people in Russia like him for when he's gone. Because if the oligarchs just take over afterwards, then One might argue, well, we had 20 good years, you know, of stability. But I mean, I would say that if we're talking about a ship of state here, the guy steering the ship, maybe if you wanted to look at it from the Russian point of view has done a great job, maybe just saying, but the rocks are still out there and he's not going to be at the at the helm forever. So, one would think that his job is to make sure that there's going to be someone who can continue to steer the ship for the people of Russia after he's gone. Now, let me ask, because I'm curious, do you? And and and ignorant. So is he doing that, do you think, is he setting it up? So that when there is no Putin the state is safe </s><s>[INST] from the beginning, That was the idea whether one of the fascinating things. Now I read every biography, english written biography and Putin. So I haven't, I need to think more deeply. But one of the fascinating things is how do power change Vladimir Putin? He was a different man when he took power than he is today. I actually in many ways admire the man that took power. I think he's very different than Stalin and Hitler at the moment. They took power. I think Hitler and Stalin were both in our previous discussion already on the trajectory of evil. I think Putin was a humble, loyal, honest man when he took power. The man he is today is worth thinking about and studying. I'm not sure that that [/INST] that's an old line about absolute power corrupting. Absolutely, </s><s>[INST] But it's you know, it's kind of a line uh you know, it's a beautiful quote, you have to really think about it, you know, like what does that actually mean? Like one of the things I still have to do, you know, I've been focusing on securing the conversation. Right? So I've been having gone through a dark place yet because I feel like I can't do the dark thing for too long. So I really have to put myself in the mind of Putin leading up to the conversation, but for now my senses his he took power when Yeltsin gave him one of the big sort of acts of the new Russia was for the first time in its history, a leader could have continued being in power and chose to give away power. That was the George Washington [/INST] you were in the United States would look at that is absolute positive, a sign, a sign of good things. Yes. </s><s>[INST] And so that was a huge act. And uh Putin said that that that was the defining thing that will define Russia for the 21st century, that act, and he will carry that flag forward. That's why In rhetoric, he after two terms, he gave away about two [/INST] Medvedev, but it was a puppet, </s><s>[INST] right? Yeah. Yes. But it was like the still the story was being told. I think he believed it early on. I think he I believe he still believes it, but I think he's deeply suspicious of the corruption that looks in the shadows. And I do believe that somebody who thinks Clickbait journalism is broken. Journalists annoy the hell [/INST] out of me. Hey, journalism is working perfectly. Journalism is broken. Journalists make things work great. </s><s>[INST] So, I understand from Putin's perspective that journalism journalists can be seen as the enemy of the state, because people think journalists write these deep, beautiful philosophical pieces about criticizing the structure of government and the proper policy would, you know, the steps that we need to take to make a greater nation. No, they they're unfairly take stuff out of context. They uh, they're critical in ways that's like shallow, not interesting. They call you a racist or sexist or they make up stuff all the time. So I can put myself in the mindset of a person that thinks that it is okay to remove that kind of shallow uh fake news voice from the system. The problem is of course that is a slippery slope to then you remove all the annoying people from the system and then you change what annoying means, which annoying starts becoming a thing that like anyone who opposes the system. I mean, I get I get the the slippery, it's obvious that it becomes a slippery slope. But I can also put myself in the mindset of the people that it's okay to remove the liars from the system as long as it's good for Russia and [/INST] okay, so here in lies and this again, the traditional american perspective, because we've had yellow, so called yellow journalism since the founding of the Republic. That's nothing new. Um, but but the problem then comes into play when you remove journalists, even, you know, it's a broad brush thing because you remove both the crappy ones who are lying and the ones who are telling the truth to your left with simply the approved government. Journalists write the ones who are towing the government's line, in which case the truth as you see it is a different kind of fake news, right? It's the fake news from the government instead of the Clickbait news and oh yeah, maybe truth mixed into all that too in some of the outlets. The problem I always have with our system here in the United States right now is trying to tease the truth out from all the falsehoods. And look, I've got 30 years in journalism. My job used to be to go through before the internet, all the newspapers and and find that I used to know all the journalists by name and I could pick out, you know, who they were and and and and I have a hard time picking out the truth from the falsehood. So I think constantly, how are people who don't have all this background, who have lives or who are trained in other specialties? How do they do it? But if the government is the only approved outlet for truth, a traditional american and a lot of other traditional societies based on these ideas of the enlightenment that I talked about earlier would see that as a disaster waiting to happen or a tyranny in progress, Does that make sense? </s><s>[INST] It totally makes sense. And I would agree with you. I still agree with you, but it is clear that something about the freedom of the press and freedom of speech in today, like literally the last few years with the internet is changing and the argument, you know, you could say that the american system of freedom of speech is broken because the here's, here's the belief I grew up on and I still hold, but I'm starting to be sort of trying to see multiple views on it. My belief was that freedom of speech results in a stable trajectory towards truth. Always. So like truth will emerge. That was my sort of faith and belief that that yeah, there's going to be lies all over the place. But there will be like a stable thing that is true that's carried forward to the public now. It feels like it's possible to go towards the world where nothing is true or truth is, is something that groups of people convince themselves of and there's multiple groups of people. And the idea of some universal truth as I suppose is the better thing is uh, is something that we can no longer exist under. Like some people believe that the Green Bay Packers is the best uh football team and some people can think the patriots and they deeply believe it to where they call the other groups liars. Now. That's fun for sports. That's fun for favorite flavors of ice cream. But they might believe that about science about uh, various aspects of uh politics, various aspects of sort of uh, different policies within the function of our government and like that's not just like some weird things to complain about, but that would be the nature of things like truth is something we can no longer [/INST] have. Well lets and let me de romanticize the american history of this too because the american press was often just as biased just as I mean I always look to the 19 seventies as the high water mark of the american journalistic, the post Watergate era where it was actively going after um uh the abuses of the government and all these things. But there was a famous speech, very quiet though very quiet given by Katharine Graham who was a Washington post editor I believe. And I actually somebody sent it to me. We had to get it off of the journalism like a j store kind of thing. And she had a at a luncheon um assured that the to the government people at the lunch and don't worry this is not going to be something that we make a trend because the position of the government is still something that was carried. The newspapers were the water and the newspapers were the big thing up until certainly the late sixties, early seventies, the newspapers were still the water carrier of the government. Right? And they were the water carriers of the owners of the newspaper. So let's not pretend there was some angelic wonderful time. And I'm saying to me because I was the one who brought it up, let's not pretend there was any super age of truthful journalism and all that. And I mean you go to the revolutionary period in american history and it looks every bit as bad as today, right? Um </s><s>[INST] that's a hopeful message actually. So things may not be as bad as they as they look more [/INST] like a stock market and that you have fluctuations in the truthfulness or or believability of the press and there are periods where it was higher than other periods. The funny thing about the so called Clickbait era and I do think it's terrible, but I mean it resembles earlier eras to me. So I always compare it to when I was a kid growing up when I thought journalism was as good as it's ever gotten. It was never perfect. Um but it's also something that you see very rarely in other governments around the world and there's a reason that journalists are often killed regularly and a lot of countries and it's because they report on things that the authorities do not want reported on. And I've always thought that that was what journalism should do. But it's got to be truthful otherwise. It's just a different kind of propaganda. Right? </s><s>[INST] Can we talk about genghis khan genghis khan by the way? Is it genghis khan genghis khan, it's not [/INST] genghis khan, it's either genghis khan genghis khan. </s><s>[INST] So let's go with Genghis khan. [/INST] The only thing I'll be able to say with any certain last certain thing </s><s>[INST] I'll say about it. It's like, I don't know GIF versus Jif, I [/INST] don't know how, I don't know how it ever got started the wrong way. </s><s>[INST] So first of all your episodes on jangles con for many people are the favorite, it's fascinating to think about events that had so much like in their ripples had so much impact on so much of human civilization in your view, was he an evil man? This ghost? Our discussion of evil? Another way to put it is I've read he's much loved and much, many parts of the world like Mongolia and I've also read arguments that say that he was quite a progressive for the time. So where do you put him? Is he a progressive or is an evil destroyer of humans? [/INST] As I often say, I'm not a historian, which is why what I've tried to bring to the hardcore history podcast are these sub themes so each show has and they're not, I try to kind of soft pedal them so they're not always like really right in front of your face. Um, in that episode, the soft pedaling sub theme had to do with what we referred to as a historical arsonist and it's because some historians have taken the position that sometimes and most of this is earlier. So historians don't do this very much anymore, but these were the wonderful questions I grew up with. That blend, it's almost the intersection between history and philosophy and the idea was that sometimes the world has become so overwhelmed with bureaucracy or corruption or just stagnation that somebody has to come in, or some group of people or some force has to come in and do the equivalent of a forest fire to clear out all the deadwood so that the forest itself can be rejuvenated and and society can then move forward. And there's a lot of these periods where the historians of the past will portray these figures who come in and do horrific things as creating an almost service for mankind, right? Creating the foundations For a new world that will be better than the old one. It's a recurring theme. And so this was the sub theme of the, of the Cons podcast, because otherwise you don't need me to tell you the story of the Mongols, but I'm going to bring up the historical arsonist element. Um and but this gets to how the con has been portrayed right. If you want to say, oh yes, he cleared out the dead would have made for, for well then it's a positive thing. If you say my family was in the forest fire that he set, you're not going to see it that way. Um much of what Genghis khan is credited with on the upside, right? So things like religious toleration and you'll say, well he was religiously the Mongols were religious religiously tolerant. And so this makes them almost like a liberal reformer kind of thing. But this needs to be seen within the context of their empire, which was very much like the roman viewpoint, which is the romans didn't care at a lot of time what your local people worshiped, they wanted stability and if that kept stability and kept you paying taxes and didn't require the legionaries to come in and and then they didn't care right. And the cons were the same way, like they don't care what you're practicing as long as it doesn't disrupt their empire and cause them trouble. But what I always like to point out is, yes, but the con could still come in with his representatives to your town, decide your daughter was a beautiful woman that they wanted in the cons concubine and they would take them. So how liberal and empire is this, right? So so many of the things that they get credit for as though there's some kind of nice guys may in another way of looking at it just be a simple mechanism of control right away to keep the empire stable. They're not doing it out of the goodness of their heart. They have decided that this is the best and I love because the Mongols were What we would call a Pagan people. Now, I love the fact that they I think we call it the term we used had to do with like, like they were hedging their bets religiously right? They didn't know which God was the right one. So as long as you're all praying for the health of the con, we're maximizing the chances that whoever the gods are, they get the message right. Um So I think it's been portrayed as something like a liberal empire and the idea of Mongo universality universality is its more about conquering the world. And it's like saying you know, we're going to bring stability to the world by conquering it. Well what if that's Hitler right? He could make the same case or Hitler wasn't really the world conqueror like that because he wouldn't have been he wouldn't have been trying to make it equal for all peoples. But my point being that it kind of takes the positive moral slant out of it if their motivation wasn't a positive moral slant to the motivate and and the Mongols didn't see it that way. And I think the way that it's portrayed is like and I would like to use this this this analogy, but it's like um shooting an arrow and painting a bull's eye around it afterwards. Right? How how do we how do we justify and make them look good in a way that they themselves probably and listen, we don't have the Mongol point of view per se. I mean there's something called the secret history of the Mongols and there's things written down by Mongolian overlords through people like Persian and chinese scribes later we don't have their point of view, but it sure doesn't look like this was an attempt to create some wonderful place where everybody was living a better life than they were before. I I think that's that's later people uh putting a nice rosy spin on it, </s><s>[INST] but there's an aspect to it. Maybe you can correct me because I'm projecting sort of my idea of what it would take to to uh to conquer so much land is uh the ideology is emergent. So if I were to guess the Mongols started out as exceptionally as warriors who valued excellence and skill of killing, not even killing, but like the actual practice of war and you can start out small, you can grow and grow and grow and then in order to maintain the stability of the things over which of the conquered lands, you developed a set of ideas with which you can, like you said, established control, but it was emergent and it seems like the core first principle idea of the Mongols is just to be excellent warriors. That felt, that felt to me like the starting point, it wasn't some ideology like with Hitler and Stalin, with Hitler, the there was an ideology that didn't have anything to do with with war underneath it. It was more about conquering, it feels like the Mongols started up more organically, I would say it's emerging like this phenomenon started emergency and they were just like similar to the native americans was the command. She's like the different warrior tribes that Joe Rogan's currently obsessed with that, what led me to look into it more, they, they seem to just start out just valuing the skill of fighting, whatever the tools of war they had, which were pretty primitive. But just to be the best warriors that could possibly be make a science out of it. Is that is that crazy to think that there was no ideology behind it. In the beginning, I'm gonna back up a second. I'm [/INST] reminded of the lines set about the romans that they create a wasteland and call it peace. That is. But there's a lot of conquerors like that, right? Um where where you will sit there and listen historians forever. It's the trade, it's the famous trade offs of empire and they'll say, well look at the trade that they facilitated and look at the religion, all those kinds of things. But they come at the cost of all those peoples that they conquered forcibly and by force integrated into their empire. The one thing we need to remember about the Mongols that makes them different than say the romans and this is complex stuff and way above my pay grade. But I'm fascinated with it and it's more like the comanches that you just brought up is that the Mongols are not a settled society. Okay. They are they are, they come from a nomadic tradition now several generations later when you have uh kubla khan as, as the, as the emperor of china, it's beginning to be a different thing, right? And the Mongols. When their empire broke up the ones that were in settled the so called settled societies, right, Iran places like that, they will become more like over time the rulers of those places were traditionally and the Mongols and say like the cognitive the golden horde which is still in their traditional nomadic territories will remain traditionally more mongol. But when you start talking about who the Mongols were, I try to make a distinction there not some really super special people. They're just the latest confederacy in an area that saw nomadic confederacy. He's going back to the beginning of recorded history. The skip the ins the sar missions, the of ours, the huns, the Magyars. I mean these are all the nomadic, you know the nomads of the Eurasian steppe were huge, huge players in the history of the world until gunpowder nullified their, their traditional weapons system, which I've been fascinated with because their traditional weapons system is not one you could copy because you were talking about being the greatest warriors. You could be every warrior society. I've ever seen values that what the what the nomads had of the Eurasian steppe was. This relationship between human beings and animals that change the equation. It was how they rode horses. And societies like the byzantines which would form one flank of the step and then all the way on the other side you had china and below that you had Persia. These societies would all attempt to create mounted horsemen who used archery and they did a good job. But they were never the equals of the nomads because those people were literally raised in the saddle. They compared them to sent ours. Um The comanches, great example considered to be the best horse riding warriors in north America. Uh The command. She's always loved watching uh there's paintings, George Catlin, the famous uh painter who painted the comanches uh illustrated it. But the Mongols and the scythians and skip the ins and the of ours and all these people did it to where they would shoot from underneath the horse's neck hiding behind the horse. The whole way you look at a picture of somebody doing that and it's insane. This is what the byzantines couldn't do and the chinese couldn't do. And it was a different level of of harnessing a human animal relationship that gave them a military advantage that could not be copied. Right? It could be emulated but they were never as good. Right. That's why they always hired these people. They hired mercenaries from these areas because they were incomparable writes the combination of people who were shooting bows and arrows from the time. They were toddlers who were riding from the time. They were who rode all the time. I mean they were the huns were bow legged. The romans said because they were never they ate slept everything in the saddle. That creates something that is difficult to copy and it gave them a military advantage. You know, I I enjoy reading actually about when that military advantage ended so 17th and 18th century when the Chinese on one flank and the Russians on the other are beginning to use firearms and stuff to break this military power of these, of these various cons um the Mongols were simply the most dominating and most successful of the confederacy is, but if you break it down, they really formed the nucleus at the top of the pyramid of the apex of the food chain. And a lot of the people that were known as Mongols were really lots of other tribes, non Mongolian tribes that when the Mongols conquer you after they killed a lot of you, they incorporated you into their confederacy. Um and often made you go first, you know, we're gonna find somebody, we're gonna make these people go out in front and suck up all the arrows before we go in and finish the job. So to me and I guess a fan of the Mongols would say that the difference and what made the Mongols different wasn't the weapons system or the fighting or the warriors or the arm or anything, it was genghis khan and if you go look at the other really dangerous from the outside world's perspective, dangerous steppe nomadic confederacy is from past history was always when some great leader emerged that could unite the tribes and you see the same thing in native american history two degree to um you had people like Attila right? Or there's one called Tuman. You go back in history and these people make the history books because they caused an enormous amount of trouble for their settled neighbors. That normally, I mean chinese Byzantine and Persian approaches to the step people were always the same. They would pick out tribes to be friendly with, they would give them money, gifts, hire them and they would use them against the other tribes. And generally Byzantine especially in chinese diplomatic history was all about keeping these tribes separated. Don't let them form confederations of large numbers of them because then they're unstoppable. Attila was a perfect example of the huns were another large the Turks, another large confederacy of these people and they were devastating when they could unite. So the diplomatic policy was don't let them. That's what made the Mongols different as Genghis khan united them. And then unlike most of the tribal confederacy is he was able, they were able to hold it together for a few generations </s><s>[INST] to linger on the little thread they started pulling on this man, Genghis khan that was a [/INST] leader. </s><s>[INST] What do you think makes a great leader. Maybe if you have other examples throughout history and great again, let's lose that use that term loosely. [/INST] He's going to ask for a definition. </s><s>[INST] Great uniter of whether it's evil or good. It doesn't matter. Uh huh is there somebody who stands out to you alexander the grace, we're talking about military or ideologies, you know, some people bring up FDR or or I mean it could be the finding fathers of this country or we can go to uh was he man a man of the century up there, Hitler of the 20th century and Stalin and these people had really a mass, the amount of power that probably has never been seen in the history of the world. Is there somebody who stands out to you by way of trying to define what makes a great uniter, great leader in one man or a woman, maybe in the future. [/INST] It's an interesting question and I would have thought a lot about because let's take alexander the Great as an example because alexander fascinated the world of his time, fascinated ever since people have been fascinated with the guy, but alexander was a hereditary monarch, right? He was handed, the kingdom is fascinating, but he did not need to rise from nothing to get that job. In fact, he reminds me of a lot of other leaders of Frederick the Great for example, in Prussia, these are people who inherited the greatest army of their day, alexander unless he was an imbecile was going to be great, no matter what, because I mean, if you inherit the very mock you're going to be able to do something with it, right alexander's father may have been greater Philip. Uh, he Philip the second was the guy who, who literally did create a, a strong kingdom from a disjointed group of people that were continually beset by their neighbors. He's the one that reformed that army, uh, took things that he had learned from other greek leaders, like the theme and leader of team a ninja's. Um and and then laboriously over his lifetime stabilized the frontiers built this system. He lost an eye doing it. He, his leg was made lame. I mean this was a man who looked like he built the empire and lead from, from the front ranks, I mean um so and then, and then who may have been killed by his son, We don't know who assassinated Philip, but then handed the greatest army the world had ever seen to his son who then did great things with it. You see this, this pattern many times in my mind, I'm not sure alexander really can be that great when you compare him to people who arose from nothing. So the difference between what we would call in the United States, the self made man or the one who inherits a fortune. There's an old line that, you know, it's, it's a slur, but it's about rich people and it's, it's like he was born on, he was born on third base and thought he hit a triple, right? Um, Philip was born at home plate and he had to hit alexander started on third base and so I try to draw a distinction between them. Genghis khan is tough because there's two traditions, the tradition that we grew up with here in the United States and that I grew up learning was that he was a self made man, but there is a tradition and it may be one of those things that's put after the fact because a lot a long time ago, whether or not you had blue blood in your veins was an important distinction. And so the distinction that you'll often hear from Mongolian history is that this was a nobleman who had been deprived of his inheritance. So he was a blue blood. Anyway, I don't know which is true. Uh, there's certainly, I mean when you look at agendas condo, you have to go, that is a wicked amount of, of things to have achieved. Uh he's very impressive as a figure until is very impressive as a figure. Um Hitler is an interesting figure. He's one of those people, you know, the more you study about Hitler, the more you wonder where the defining moment was because um if you look at his life, Hitler was a relatively common soldier in the First World War. I mean he was brave, he got uh he got some decorations. In fact, the highest decoration he got in the First World War was given to him by a jewish officer and it was uh, he often didn't talk about that decoration, even though it was the more prestigious one because it would open up a whole can of worms you didn't want to get into. But Hitler's, I mean if you said who was Hitler today, one of the top things you're going to say is he was an anti Semite. Well then you have to draw a distinction between general regular anti Semi Semitism that was pretty common in the era and something that was a rabid level of anti Semitism. But Hitler didn't seem to show a rabid level of of anti Semitism until after or at the very end of the First World War. So if this is a defining part of this person's character and much of what we consider to be his, his evil stems from that. What happened to this guy when he's an adult, right, He's already fought in the war to change him. So, I mean it's almost like the old, there was always a movie theme. Somebody gets hit by by something on the head and their whole personality changes, right? I mean it almost seems something like that. So I don't think I call that necessarily a great leader. To me, the interesting thing about Hitler is What the hell happened to a nondescript person who didn't really impress anybody with his skills. And then in the 1920s is all of a sudden, as you said, sort of the man of the hour, right? So that to me is kind of, I have this feeling that Genghis Khan and we don't really know was an impressive human being from the get go and then he was raised in this environment with pressure on all sides. You start with this diamond and then you polish it and you harden it his whole life. Hitler seems to be a very unimpressive gemstone most of his life and then all of a sudden, so I mean, I don't think I can label great leaders and I'm always fascinated by that idea that I'm trying remember who the quote was by that great men, Lord Acton. So great men are often not good men. Uh and that in order to be great, you would have to jettison many of the moral qualities that we normally would consider, jesus or Gandhi or you know, martin these qualities that one looks at as, as the good upstanding moral qualities that we should all aspire to as examples, right? The buddha, whatever it might be. Um those people wouldn't make good leaders because what you need to be a good leader often requires the kind of choices that a true philosophical diogenes moral man wouldn't make. Um so I don't have an answer to your question, How about that? That's a very long way of saying, </s><s>[INST] I don't know, just linger a little bit, it does feel like from my study of Hitler that the time molded demand versus genghis khan where it feels like he, the man molded his time. [/INST] And I feel that way about a lot of those nomadic confederacy builders, that they really seem to be these figures that stand out as extraordinary for one in one way or another, remembering by the way that almost all the history of them were written by the enemies that they so mistreated, that they were probably never going to get any good press. They didn't write themselves. That's a </s><s>[INST] caveat. We should always have basically, [/INST] no matter where native american peoples or tribal peoples anywhere generally do not get the advantage of being able to write the history of their heroes. </s><s>[INST] Okay, I've uh have recently almost done with the rise in the fall of the third Reich, one of the historical descriptions of Hitler's rise to power. Nazis rise to power. There's there's a few philosophical things I'd like to uh, ask you to see if you can help, Like, one of the things I think about is uh, how does one Be a hero in 1930s, Nazi Germany, what does it mean to be a hero? What do heroic actions look like? I think about that, because I think about how I move about in this world today, you know, that we live in really chaotic, intense times where I don't think you want to draw any parallels between Nazi Germany and modern day in any of the nation's can think about, but it's not out of the realm of possibility that authoritarian governments take hold. Authoritarian companies take hold. And I'd like to think that I could be in my little small way and inspire others to take the heroic action before things get bad. And I kind of try to place myself in what would 1930s Germany look like. Is it possible to stop a Hitler? Is it even the right way to think about it? And how does one be a hero in it? I mean, you often talk about that, living through a moment in history is very different than looking at that history. Looking, you know, when you look back, I also think about it, would it be possible to understand what's happening that the bells of war are ringing? Uh, it seems that most people didn't seem to understand, you know, late into the 30s, that war is coming. That's fascinating on the United States side. Inside Germany, like the opposing figures, the german military didn't seem to understand this. Maybe, uh, the other country certainly France. And uh, England didn't seem to understand this, that kind of tried to put myself into nineties thirties, Germany as I'm jewish, which is another little twist on the whole, like, what would I do? What should one do? Do you have interesting answers? [/INST] So earlier, we had talked about Putin and we had talked about patriotism and love of country and those sorts of things in order to be a hero in Nazi Germany by our views here, you would have had to have been anti patriotic to the average Germans viewpoint in the 19 thirties, right? You would have to have opposed your own government and your own country. And that's a very it would be a very weird thing to go to people in Germany and say, listen, the only way you're going to be seen as, as, as a good german and a hero to the country that will be your enemies is we think you should oppose your own government. It's it's a strange position to put the people in a government and saying you need to be against your leader, you need to oppose your government's policies. You need to oppose your government. You need to hope and work for its downfall. That doesn't sound patriotic. It wouldn't sound patriotic here in this country. If you if you made a similar argument, um I will go away from the 1930s and go to the 1940s to answer your questions. So there's movements like the White Rose movement in Germany, which involved young people really, and and from various backgrounds, religious backgrounds, often who worked openly against the Nazi government at a time when power was already consolidated the gestapo was in full force and they execute people who are against the government and these young people would go out and distribute pamphlets and many of them got their heads cut off with guillotines for their trouble. And they knew that that was going to be the penalty. That is a remarkable amount of bravery and sacrifice and willingness to die. And almost not even willingness because they were so open about it. It's almost a certainty, right? Um that's incredibly moving to me. So when we talk and we talked earlier about sort of the human spirit and all that kind of thing. There are people in the german military who opposed and worked against Hitler for example. But to me that's almost cowardly compared to what these young people did in the White Rose movement, because those people in the in the Wehrmacht for example, who were secretly trying to undermine Hitler. They're they're they're not really putting their lives on the line to the same degree. Um and so I think when I look at heroes and listen, I remember once saying there were no conscientious objectors in Germany as a way to point out to people that you didn't have a choice, You know, you were going to serve in there. And I got letters from Jehovah's witnesses who said yes, there were, and we got sent to the concentration camps. Those are remarkably brave things. It's one thing to have your own set of standards and values. It's another thing to say, oh no, I'm going to display them in a way that with this regime, that's a death sentence and not just for me for my family, right in these regimes, there was not a lot of distinction made between father and son and wives. That's a remarkable sacrifice to make and far beyond what I think I would even be capable of. And so the admiration comes from Seeing people who appear to be more morally profound than you are yourself. Um, so when I look at this, I look at that that kind of thing. And I just say, Wow! And the funny thing is if you have gone to most average Germans on the street in 1942 and said, what do you think of these people? They're going to think of them as traitors who probably got what they deserved. So that's the eye of the beholder thing. It's the power of the state to um to so propagandized values and morality in a way that favors the state that you can turn people who today we look at is unbelievably brave and moral and crusading for righteousness and turn them into enemies of the people. Um, so I mean, in my mind, it would be people like that. </s><s>[INST] CIA, I think so, hero is a funny word. We romanticize the notion, but if I could drag you back to 19 thirties, Germany from 19 forties, I feel like the heroic actions that doesn't accomplish much is not what I'm referring to. So there's many heroes. I look up to that, uh, like David Goggins, for example, the guy who runs crazy distances. He runs for no purpose except for the suffering in itself. And I think his willingness to challenge the limits of his mind is heroic. I guess I'm looking for a different term, which is how could Hitler have been stopped. My sense is that he could have been stopped in the battle of ideas. Where people, millions of people were suffering economically were suffering because of the betrayal of World War One in terms of the love of country and how they felt they were being treated and charismatic leader that inspired love and unity that's not destructive could have emerged. And that's where the battle should have been fought. [/INST] I would suggest that we need to take into account the context of the times </s><s>[INST] that led to Hitler's [/INST] rise of power and created the conditions where his message resonated. That is not a message that resonates at all times, right. Um It is impossible to understand the rise of Hitler without dealing with the First World War and the aftermath of the First World War and the inflationary terrible depression in Germany and all these things and the dissatisfaction with the Weimar Republic's government, which was often seen as a, as something put into which it was put into place by the victorious powers. Hitler referred to the people that signed those agreements that signed the armistice as the november criminals. And he used that as a phrase which resonated with the population. This was a population that was embittered. and even if they weren't embittered, the times were so terrible and the options for operating within the system in a non radical way seemed totally discredited, right? You can work through the Weimar Republic, but they tried and it wasn't working anyway. And then the alternative to the nazis who were bully boys in the street were communist agitators. That to the average conservative Germans seem no better. So you have three options. If you're an average german person, you can go with the discredited government put in power by your enemies that wasn't working anyway. You could go with the nazis who seemed like a bunch of super patriots calling for the restoration of german authority or you could go with the communists and the entire thing seemed like a litany of poor options. Right? And in this realm, Hitler was able to triangulate if you will, um he came off as a person who was going to restore german greatness at a time when this was a powerful message. But if you don't need german greatness restored, it doesn't resonate. Right. Um So the reason that your love idea and all this stuff, I don't think would have worked in the time period is because that was not a commodity that the average german was in search of then Well, </s><s>[INST] it's interesting to think about whether greatness can be restored through mechanisms through ideas that are not. So from our perspective today, so evil, I don't know what the right term is, [/INST] but the war continued in a way. So remember that that when Germany, when Hitler is rising to power, the french are in control of parts of Germany, right? The Ruhr uh one of the main industrial heartlands of Germany was occupied by the french. So there's never this point where you're allowed to let the hate dissipate right every time, maybe things were calming down, something else would happen to stick the knife in and twist it a little bit more from the average Germans perspective. Right? Um the reparations, right? So if you say, okay, well, we're going to get back on our feet, the reparations were crushing these things prevented the idea of love or brotherhood and all these things from taking hold. And even if there were Germans who felt that way and they most certainly were, it is hard to overcome the power of everyone else. You know what I always say when people talk to me about humanity, is I believe on an individual levels were capable of everything and anything good, bad or indifferent, but collectively it's different, right? And in the time period that we're talking about here, messages of peace on earth and love, your enemies and and all these sorts of things were absolutely delusion and overwhelmed and drowned out by the bitterness, the hatred and let's be honest, the sense that you were continually being abused by your former enemies, there were a lot of people in the allied side that realize this and said, we're setting up the next war. This is I mean, they understood that you can only do certain things to collective human populations for a certain period of time before it is natural for them to want to. And you can see german posters from the region, Nazi propaganda posters that show them breaking off the chains of their enemies. And I mean, Germany awake, right, That was the great um slogan. So I think love is always a difficult option and in the context of those times it was even more disempowered than normal. </s><s>[INST] Well, this goes to the, just to linger in it for a little longer. The question of the inevitability of history, Do you think Hitler could have been stopped. Do you think this kind of force that you're saying that there was a pain and those building, there's a hatred that was building? Do you think there was a way to avert? I mean, there's two questions, could have been a lot worse and could it have been better In the trajectory of history in the 30s and 40s, [/INST] the most logical. See we had started this conversation brings a wonderful bow tie into the discussion and buttons it up nicely. We had talked about force and Counterforce earlier, uh, the most obvious and and much discussed way that Hitler could have been stopped has nothing to do with Germans um when he re militarized the Rhineland, everyone talks about what a couple of french divisions would have done, had they simply gone in and contested? And this was something Hitler was extremely, I mean, it might have been the most nervous time in his entire career because he was afraid that they would have responded with force and he was in no position to do anything about it if they did. So this is where you get the people who say um you know, and Churchill is one of these people to where they talk about uh that that you know, he should have been stopped militarily right at the very beginning, when he was weak. I don't think uh listen, there were candidates in the in the catholic center Party and others in the Weimar Republic that maybe could have done things and it's beyond my understanding of specific german history to talk about it intelligently. But I do think that had the french responded militarily to Hitler's initial moves into that area, that he would have been thwarted. And I think he himself believed if I'm remembering my reading um that this would have led to his downfall. So the potential, what I don't like about this is that it almost legitimizes military intervention at a very early stage to prevent worse things from happening, but it might be a pretty clear cut case, but it shows that we pointed out that there was a lot of sympathy on the part of the Allies for the fact that, you know, the Germans probably should have Germany back and this is traditional german land. And I mean, they were trying in a funny way, it's almost like the love and the sense of justice on the Allies part may have actually stayed their hand in a way that would have prevented much, much, much worse things later. But if the times were such that the message of a Hitler resonated than simply removing Hitler from the equation would not have removed the context of the Times. And that means one of two things. Either you could have had another one or you could have ended up in a situation equally bad in a different direction. I don't know what that means because it's hard to imagine anything could be worse than what actually occurred. But history is funny that way. And that Hitler always, everyone's favorite example of the difference between the Great Man theory of history and the trends and forces, theories of history, right? The times made a Hitler possible and maybe even desirable to some, if you took him out of the equation, those trends and forces are still in place. Right? So what does that mean? If you take him out and the door is still open to somebody else walk through it. </s><s>[INST] Yeah, it's mathematically speaking, the the probability of charismatic leaders emerge. I'm so torn on that. I'm uh at this point, [/INST] here's another way to look at it? The institutional um stability of Germany in that time period was not enough to push back? And there are other periods in german history. I mean, that Hitler Arose in Arisen in 1913. He doesn't get anywhere because Germany's institutional power is enough to simply quash that it's the fact that Germany was unstable anyway, that prevented a united front. That would have kept radicalism from getting out of hand. Does it make sense? </s><s>[INST] Yes, absolutely. A tricky question on this, just to stay in this a little a longer, because I'm not sure how to think about it is the World War Two versus the holocaust. We were we were talking just now about the way the history unrolls itself and could Hitler have been stopped and I don't quite know what to think about Hitler without the holocaust and perhaps in his thinking how essential the anti Semitism and the hatred of jews was it feels to me that, I mean, I don't, we were just talking about where did he pick up his hatred of the jewish people? There's their stories in Vienna and so on that it almost is picking up the idea of anti Semitism as a really useful tool as opposed to actually believing in this core? Do you think World War Two as it turned out and Hitler as he turned out would be possible without anti Semitism. Could we have avoided the holocaust or was it an integral part of the ideology of fascism and the nazis [/INST] not an integral part of fascism? Because Mussolini really, I mean, Mussolini did it to please Hitler, but it wasn't an integral part. What's interesting to me is that that's the big anomaly in the whole question, because anti Semitism didn't need to be a part of this at all. Right, Hitler had a conspiratorial view of the world. He was a believer that the jews controlled things, right? The jews were responsible for both bolshevism on one side and capitalism on the other. They ruled the banks in the United States was a jew ified country, right, bolshevism was a jew ified sort of a political, in other words, he saw jews everywhere, and he had that line about if the jews of europe, uh, force another war to Germany, they'll pay the price or whatever. But then you have to believe that they're capable of that the holocaust is a weird weird sidebar to the whole thing. And here's what I've always found interesting. It's a sidebar that week in Germany because look at the first World War, jews fought for Germany, right? Who was the most important? And this is a very arguable point, but it's just the first one that pops into my head, who was the most important jewish figure that would have maybe been on the german side, had the Germans had a non anti Semitic, Well, listen, that whole part of Yeah, but, but the whole, I should point out that is to say Germany or europe or Russia or any of those things were not anti Semitic is to do injustice to history, right? Programs every I mean that is that it's standard operating procedure, what you see in the hitlerian era is an absolute huge spike because the government has a conspiracy theory that the jews have. It's funny because Hitler both thought of them as weak and super powerful at the same time, right? And and and as an outsider people that we can I mean the whole idea of the blood and how that connects to Darwinism and all that sort of stuff is just weird, right? A real outlier. But Einstein, let's just play with Einstein if there's no anti Semitism in Germany or or none above the normal level, right? Um the baseline level um design stein leave along with all the other uh jewish scientists and I mean, and what does Germany have as as increased technological and intellectual capacity if they stay right, it's something that actually weakened that state. It's it's a tragic flaw in the hit larian worldview, but it was so, and I don't let me you had mentioned earlier, like maybe it was not integral to his character. Maybe it was a wonderful tool for power, I don't think so, somewhere along the line and really not at the beginning, this guy became absolutely obsessed with this conspiracy theory and jews and and he surrounded himself with people and theorists, I'm going to use that work really, really sort of loosely who believed this too. And so you have a ca ball of people who are reinforcing this idea that the jews control the world that he called it international jewelry was a huge part of the problem and because of that they deserve to be punished. They were an enemy within all these kinds of things. It's a nutty conspiracy theory that the government of one of the most, I mean, the big thing with Germany was culture, right? They were they were they were a leading figure in in culture and philosophy and all these kinds of things and that they could be overtaken with this wildly wickedly weird conspiracy theory and that it would actually determine thing. I mean, Hitler was taking vast amounts of german resources and using it to wipe out this race when he needed them for all kinds of other things to fight a war of annihilation. So that is the weirdest part of of the whole Nazi phenomenon. It's </s><s>[INST] the darkest possible silver lining to think about is that the holocaust may have been in the hatred of the jewish people, may have been the thing that avoided Germany Getting The Nuclear Weapons 1st. And s [/INST] Mhm Isn't that a wonderful historical ironic twist that if it weren't so over laid with tragedy 1000 years from now will be seen as something really kind of funny? Well, </s><s>[INST] that's, that's true. It's fascinating to think, as you've talked [/INST] the seeds of his own destruction, right? The tragic flaw </s><s>[INST] and my hope is this is a discussion I have with my dad is a physicist. Yeah, yeah. Is that evil inherently contains with it, that kind of incompetence. So my dad's discussions, he's a physicist and engineer. His belief is that at this time in our history, the reason we haven't had nuclear, like uh terrorist, uh, blow up a nuclear weapon somewhere in the world is that the kind of people that would be terrorists are simply not competent enough at their job of being destructive. So like there's a kind of, if you plot it, the more evil you are, the less able you are and by evil. I mean purely just like you said, uh if we were to consider the hatred of the jewish people is evil because it's sort of detached from reality, it's like, like just this pure hatred of something that's grounded on things, you know, conspiracy theories, if that's evil, then the more you sell yourself, the more you give into these conspiracy theories, the less capable you are actually engineering, which is very difficult, engineering nuclear weapons and effectively deploying them. So that's the, that's a hopeful message that the destructive people in this world are by their worldview, incompetent in creating the ultimate destruction. I don't agree with that? [/INST] Oh boy, I straight up don't agree with that. </s><s>[INST] So why are we still here? Why haven't we destroyed ourselves? Why haven't the terrorist blow has been many decades? Why haven't we destroyed ourselves to this point? [/INST] Well, when you say it's been many decades, many days, it's like saying in the, in the life of 100 and 50 year old person, uh, we've been doing well for a year. The problem, the problem with all these kinds of equations and it was Bertrand Russell, right, the philosopher who said so, he said it was, it's unreasonable to expect a man to walk on a tight rope For 50 years. I mean, the problem is, is that this is a long game. And let's remember that up until relatively recently, what would you say? 30 years ago, the nuclear weapons in the world were really tightly controlled. That was one of the real dangers in the fall of the Soviet Union. Remember the worry that that all of a sudden you were going to have bankrupt former soviet republic selling nuclear weapons to terrorists and whatnot, I would suggest. And here's another problem is that when we call these terrorists evil, it's easy for an american for example, to say that Osama bin laden is evil, easy for me to say that, but one man's terrorist is another man's freedom fighter, as the saying goes and two other people, he's not what Osama bin laden did. Um, and the people that worked with him, we would call evil genius, the idea of hijacking planes and flying them into the buildings like that and that he could pull that off and that still boggles my mind. I'm still, it's funny, I'm still stunned by that and yet, you know, the idea here's the funny part and I don't, I hesitate to talk about this because I don't want to give anyone ideas, but you don't need nuclear weapons to do incredibly grave amounts of danger really. I mean, what one can of gasoline and a big lighter can do in the right place and the right time and over and over and over again can bring down societies. This is the argument behind the importance of the stability that a nation state provides. So when we went in and took out Saddam Hussein, one of the great counter arguments from some of the people who said this is a really stupid thing to do is that Saddam Hussein was the greatest anti terror weapon in that region that you could have because they were a threat to him. So he took that and he did it in a way that was much more repressive than we would ever be right. And this is the old line about why we supported um right wing Death squad countries because they were taking out people that would inevitably be a problem for us if they did and they were able to do it in a way we would never be able to do supposedly were pretty good at that stuff. You know, just like the soviet union was behind the scenes and underneath the radar. But the idea that the stability created by powerful and strong centralized leadership allowed them, it's almost like outsourcing anti terror activities allowed them to for their own reasons. I mean you see the same thing in the serious situation with the assad's. I mean you can't have an ISIS in that area because that's a threat to the assad government who will take care of that for you and then that helps us by not having an ISIS. So um I would suggest one that the game is still on, on whether or not these people get nuclear weapons in their hands. I would suggest they don't need them to achieve their goals. Really, The crazy thing is if you start thinking like the joker in batman, the terrorist ideas, it's funny, I guess I would be a great terrorist because I'm just full of those ideas. You can do this. It's scary to think of how vulnerable we are. But the whole point </s><s>[INST] is that you as the joker wouldn't do the terrorist actions. That's the that's the theory. That's so hopeful to me with my dad. Is that all the ideas, your ability to generate good ideas. What forget nuclear weapons, how you can disrupt the power grid, how you can disrupt the attack? Our psychology attack, like with a can of gasoline, like you said somehow disrupt the american system of ideas like that coming up with good ideas there? [/INST] Are we saying evil people can't come up with evil genius ideas. </s><s>[INST] That's what I'm saying. We have this Hollywood story. [/INST] I don't think history backs that up. I mean, I think you can say with the nuclear weapons it does, but only because they're so recent, but I mean evil genius, I mean that's almost proverbial, </s><s>[INST] but that's okay. So to push back for the fun of it or [/INST] I don't need to I don't want you to leave this for the in a terrible mood because I pushed back on every hopeful idea. But I tend to be a little cynical about that </s><s>[INST] stuff. But but that goes to the definition of evil I think because I'm not so sure human history has a lot of evil people being competent. I do believe that they mostly like in order to be good at doing what may be perceived as evil, You have to be able to construct an ideology around which you truly believe when you look in the mirror, buy yourself that you're doing good for the world. And it's difficult to construct an ideology where destroying the lives of millions or disrupting the american system. I'm already contradicting myself as [/INST] I was saying to say people have done this already. </s><s>[INST] So, but but then it's the question of like about aliens with the the idea that if the aliens are all out there, why haven't they visited us? The same question? If it's so easy to be evil? Not easy if it's possible to be evil, why haven't we destroyed ourselves? And your statement is from the context of history, the game is still on and it's just been a few years since we've found the tools to destroy ourselves and one of the challenges of our modern time, we don't often think about this pandemic kind of revealed how soft we've gotten in terms of our deep dependence on the system. So somebody mentioned to me, you know what happens if power goes out for a day? What happens if power goes out for um a month over the person that mentioned this was a Berkeley faculty that I was talking with. He's an astronomer who was observing solar flares and it's very possible that a solar flare, they happen all the time to different degrees. [/INST] Yeah. </s><s>[INST] To knock out the power grid for months. So like, you know, just as a thought experiment, what happens if just power goes out for a week in this country, like [/INST] the electro magnetic pulses in the nuclear weapons and all those kinds of things? But maybe </s><s>[INST] that's an act of nature and even just the act of nature will reveal like a little the fragility of it all and then the evil can emerge. I mean the kind of things that might happen when power goes out, especially during a divisive time. [/INST] Well, you won't have food at baseline level. That would mean that the the the entire supplies chain begins to break down and then you have desperation and desperation opens the door to everything. </s><s>[INST] Can I ask a dark question [/INST] as opposed to the other things we've been talking about? </s><s>[INST] There's always a threat, a hopeful message. I think it will be a hopeful message on this one [/INST] too. They have the wrong </s><s>[INST] guess. Just saying, uh, if you were to bet money on the way that human civilization destroys itself or it collapses in some way, that is where the result would be unrecognizable to us as anything akin to progress. What would you say? Is it nuclear weapons? Is it some societal breakdown through just more traditional kinds of war? Is it engineered pandemics, nanotechnologies, that artificial intelligence? Is it something we can't even expect yet? Do you have a sense of how we humans will destroy ourselves or might we live forever? [/INST] I think what governs my view of this thing is the ability for us to focus ourselves collectively? Right. And that gives me the choice of looking at this and saying, what are the odds? We will do X versus why? Right. Um, so go look at the 62 Cuban missile crisis where we look at the potential of nuclear war and we stared right in the face of that to me, I consider that to be you want to talk about a hopeful moment, that's one of the rare times in our history where I think the odds were overwhelmingly that there would be a nuclear war and I'm not the super Kennedy worshiper that, you know, I grew up in an era where he was, especially amongst people in the Democratic Party. He was almost worshiped and I was never that guy. But I will say something john f Kennedy by himself, Um, probably made decisions that saved 100 million or more lives because everyone around him thought he should be taking the road that would have led to those deaths and to push back against that is when you look at it now, I mean, again, if you were a betting person, you would have bet against that, and that's rare, right? Um, so, so when we talk about how the world will end, um, the fact that one person actually had that in their hands meant that it wasn't a collective decision, it gave, remember I said, I trust people on an individual level, but when we get together, we're more like a herd and we devolve down to the lowest common denominator. That was something where the higher ethical ideas of a single human being could come into play and make the decisions that influence the events. But when we have to act collectively, I get a lot more pessimistic. So take what we're doing to the planet and we talk about it always now in terms of climate change, which I think is far too narrow. Uh, look at you, you know, and I always get very frustrated when we talk about these arguments about, is it happening? Is human? Just look at the trash, forget, forget climate for a second. We're destroying the planet because we're not taking care of it. And because what it would do to take care of it would require collective sacrifices. That would require enough of us to say, okay, and we can't get enough of us to say, okay, because too many people have to be on board. It's not john f Kennedy making one decision from one man, we have to have 85% of us or something around the world, not just you can't say we're going to stop doing damage to the, to the, to the world here in the United States, if china does it right. So the amount of people that have to get on board that train is hard. You get pessimistic hoping for those kinds of shifts, unless it's right, Krypton is about to explode. We have, and so I think if you're talking about a gambling man's view of this, that that's got to be the odds on favorite because it requires such a unified, I mean, and the systems maybe aren't even in place, right? The fact that we would need intergovernmental bodies that are completely discredited now on board and you would have to subvert the national interests of nation states, I mean, the the amount of things that have to go right In a short period of time where we don't have 600 years to figure this out, right? So to me that that looks like the most likely just because the things we would have to do to avoid, it seemed the most unlikely. Does that make sense? </s><s>[INST] Yes, absolutely. I I believe call me naive and just like you said with the individual, I believe that charismatic leaders, individual leaders will save us, like, [/INST] you don't get them all at the same time. What if you get a charismatic leader in one country? But what if you get a charismatic leader in a country that doesn't really matter that much? </s><s>[INST] Well, it's a ripple effect, so it starts with one leader and their charisma inspires other leaders, like, so it's uh it's like one and queen steps up and then the rest of the and start behaving and then there's like little other spikes of leaders that emerge, and then that's where collaboration emerges. I tend to believe that like, when you heat up the system and shit starts getting really chaotic, then the leader, whatever this collective intelligence that we've developed the leader will emerge? Like, do you think [/INST] there's just as much of a chance though that the leader would emerge and say the jews are the people who did all this, you know what I'm saying is that the idea that they would come up, you have a charismatic leader and he's going to come up with the rights or she is going to come up with the right solution as opposed to totally coming up with the wrong solution. I mean, I guess what I'm saying is you could be right, but a lot of things have to go the right way, </s><s>[INST] but my intuition about the evolutionary process that led to the creation of human intelligence and consciousness on earth, Mhm results in the the power of like if we think of it, just the love and the system versus the hate in the system that the love is greater. The human, the human kindness potential in the system is greater than the human hatred potential. And so the leader that is in the time when it's needed, the leader that inspires love and kindness will is more likely to emerge and we'll have more power. So you have the hitlers of the world that emerge, but they're actually in the grand scheme of history, are not that impactful. So it's weird to say, but not that many people died in World War Two, if you look at the full range of human history, you know, it's uh up to 100 million, whatever that is with natural pandemics too, you can have those kinds of numbers, but it's still a percentage, I figure what the percentage is, maybe 35% of the human population on earth. Maybe it's a little bit focused on a different region, but it's not destructive to the entirety of human civilization. So the, I believe that the, the charismatic leaders one time is needed that do good for the world in the broader sense of good are more likely to emerge than the ones that say kill all the jews. It's [/INST] Possible though. And this is just, you know, I've thought about this all of 30 seconds. But I mean, uh, it we're </s><s>[INST] Betting money here on the, on the 21st century who's going [/INST] to win? I think maybe you divided this into too much of a black and white dichotomy. This love and good on one side and this evil on another, let me throw something that might be more in the center of that linear a balancing act, self interest, which may or may not be good, you know, good, the good version of it we call enlightened self interest, write the bad version of it. We call selfishness, but self interest to me seems like something more likely to impact the outcome than either love on one side or evil on the other. Simply a question of what's good for me or what's good for my country or what's good from my point of view or what's good for my business. I mean, if you tell me, um, and I maybe I'm a coal miner or maybe I own a coal mine. If you say to me, we have to stop using coal because it's hurting the earth. I have a hard time disentangling that greater good question from my right now, good feeding my family question. Right? So I think, I think maybe it's going to be a much more banal thing than good and evil, much more a question of we're not all going to decide at the same time that the interests that we have are aligned. Does that make sense? Yeah, </s><s>[INST] totally. But I mean, I've looked at I mean rand and objectivism and kind of really thought like how bad or good can things go when everybody's acting selfishly? But I think we're just talking to ants here with microphones talking about. But like the question is when they when this spreads. So what what is, what do I mean by love and kindness? I think it's human flourishing on earth and throughout the cosmos, it feels like whatever the engine that drives human beings is more likely to result in human flourishing. And people like Hitler are not good for human flourishing. So that's what I mean by good is they is is there's uh I mean maybe it's an intuition that kindness is an evolutionary advantage. I hate those terms. I hate to reduce stuff to uh evolutionary biology always, but it just seems like for us to multiply throughout the universe. It's good to be kind to each other and those leaders will always emerge to save us from the hitlers of the world that want to kind of burn the thing down with a flamethrower. That's the intuition. [/INST] But let's talk about, you know, you brought up evolution several times. Let me play with that for a minute. Um I think going back to animal times, we are conditioned to deal with overwhelming threats right in front of us. So I have quite a bit of faith in humanity when it comes to impending doom right outside our door. Uh if Krypton is about to explode, I think humanity can rouse themselves to great and would give power to the people who needed it and be willing to make the sacrifices. But that's what makes, I think the pollution slash climate change slash you know, screwing up your environment, uh threats so particularly insidious is it happens slowly, right? It defies fight and flight mechanisms. It defies the natural ability we have to deal with the threat that's right on top of us. And it requires an amount of foresight that while some people would be fine with that, most people are too worried and understandably, I think too worried about today's threat rather than next generations threat or whatever it might be. So, I mean when we talk about when you said, what do you think the greatest threat is? I think with nuclear weapons, I think could we have a nuclear war we darn right? Could, but I I think that there's enough of inertia were against that because people understand instinctively if I decide to launch this attack against china and I'm India we're going to have 50 million dead people tomorrow. Whereas if you say we're going to have a whole planet of dead people in three generations, if we don't start now, I think the evolutionary, uh, way that we have have, have evolved mitigates maybe against that. In other words, I think I would be pleasantly surprised if we could pull that off. Does that make sense? Totally? I don't mean to be like, I'm not suspecting doom was </s><s>[INST] it's fun that way. I think we're both, maybe I'm over the top on the love, [/INST] maybe I'm over the top on the do. </s><s>[INST] So it makes, it makes for a fun chat. I think so, 11 guy that I've talked to several times just solely becoming a friend is a guy named Elon musk. He's a big fan of hardcore history, especially Jenkins Con a series of episodes, but really all of it, him and his, his girlfriend grimes, listen to it. I know, you know, you're on okay, awesome, so that's like relationship goals. Uh, like listen to hardcore history and the weekend with your loved one. Okay, uh, so let me, if I were to look at the guy from a perspective of human history, it feels like he will be a little speck that's remembered? [/INST] Oh absolutely. You </s><s>[INST] think about like the people, what will we remember from our time, Who are the people will remember whether it's the The Hitlers or the Einstein's who's going to be, It's hard to predict when you're in it, but it seems like Ellen would be one of those people remembered and if I were to guess what he's remembered for, it's the work he's doing with SpaceX and potentially being the person we don't know, but being the person who launched a new era of space exploration, if you look, you know, centuries from now, if we are successful as human beings surviving long enough to venture out into the october the stars, it's weird to ask you this, I don't know what your opinions are, but do you think humans will be a multi planetary species in the arc, a long arc of history? Do you think Ellen will be successful in his dream? And he doesn't, he doesn't shy away from saying it this way. Right. He really wants us to colonize mars first and then colonize other earth like planets in other solar systems throughout the galaxy. Do you have a hope that we humans will venture out towards the stars? [/INST] So here's the thing and this actually again dovetails do what we were talking about earlier. I actually, first of all, I toured SpaceX and it is when, you know, it's hard to get your mind around because he's doing what it took governments to do before. Okay, so, so it's incredible that we're watching individual companies and stuff doing this during a faster and cheaper. Yeah. Well, and, and, and pushing the envelope right faster than the government at the time we're moving. It's it's, it really is. I mean, there's a lot of people who I I think who think Ellen is overrated and you have no idea right? When you go see it, you have no idea. But that's actually not what I'm most impressed with. Um, it's Tesla, I'm most impressed with. And the reason why is because in my mind, we just talked about what I think is the greatest threat, the environmental stuff. And I talked about our inability maybe all at the same time to be willing to sacrifice our self interests in order for the, for the goal. And I don't want to put words in Elon's mouth. So you can, you can talk to him if you want to. But in my mind, what he's done is recognize that problem. And instead of building a car that's a piece of crap. But you know, it's good for the environment. So you should drive it. He's trying to create a car that if you're only motivated by your self interest, you'll buy it anyway and it will help the environment and help us transition away from one of the main causes of damage. I mean, one of the things this pandemic and the shutdown around the world has done is show us how amazingly quickly the earth can actually rejuvenate. We're seeing clear skies in places species come and you would have thought it would have taken decades for some of this stuff. So what if to name just one major pollution source? We didn't have the pollution caused by automobiles. Right? And, and if if you had said to me dan, what do you think? The odds of us transitioning away from that were 10 years ago? I would have said, well, people are going to do it because it's inefficient. It's this, it's that nobody wants to both. But what if you created a vehicle that was superior in every way so that if you were just a self oriented consumer, you'd buy it because you wanted that car. That's the best way to get around that problem of people not wanting to, I think he's identified that. And as he's told me before, you know, when the last time a car company was created, that actually, you know, blah, blah, blah, he's right. And so I happen to feel that even though he's pushing the envelope on the space thing, I think somebody else would have done that someday. I'm not sure because of the various things he's mentioned how difficult it is to start there. I'm not sure that the industries that create vehicles for us would have gone where he's going to lead them. If he didn't force them there through consumer demand by making a better car that people want it anyway, they'll follow, they'll copy they'll do all those things and yet who was going to do that? Um, so I hope he doesn't hate me for saying this, but I happen to think the Tesla idea may alleviate some of the need to get off this planet because the planet is being destroyed, right? And we're going to colonize mars probably anyway, if we live long enough. And I think the Tesla idea, not just Elon's version, but ones that follow from other people is the best chance of making sure we're around long enough to see mars colonize. Does that make sense? Yeah, </s><s>[INST] totally. And one other thing from my perspective, because I'm now starting a company. I think the interesting thing about Ellen as he serves as a beacon of hope, Like pragmatically speaking for people that sort of to push back on our doom conversation from earlier that a single individual could build something that allows us as self interested individuals to gather together in a collective way to actually alleviate some of the dangers that face our world. So like it gives me hope as an individual, that I could build something that can actually have impact that counter acts the the Stalin's and the Hitlers and all the threats that face uh that human civilization faces, that an individual has that power. I didn't believe that the individual has that power in the, in the halls of government. Like I don't feel like anyone presidential candidate can rise up and help the world unite the world. It feels like from everything I've seen and you're right with Tesla, it can bring the world together to do good. That's a really powerful mechanism of, you know, whatever you say about capitalism, that you can build companies that start, you know, it starts with a single individual. Of course, there's a collective that that grows around that, but the leadership of a single individual, their ideas, their dreams, their vision can catalyze something that takes over the world and does good for the entire world. [/INST] But if I think, but again, I think the genius of the idea is that it doesn't require us to go head to head with human nature, right? He's he's actually built human nature into the idea by basically saying, I'm not asking you to be, uh, an environmental activist, I'm not asking you to sacrifice to make it, I'm going to sell you a car, you're going to like better and by buying it, you'll help the environment that takes into account our foibles as a species and actually leverages that to work for the greater good. And that's the sort of thing that does turn off my little doom casters cynicism thing a little bit because you're actually hitting us where we live, right? You're you're you're not you can take somebody who doesn't even believe the environments a problem, but they want a Tesla. So they're inadvertently helping anyway. I think that's the genius of the idea. </s><s>[INST] Yeah. And I'm telling you that's one way to make love. Much more efficient mechanism of change than hey, [/INST] making it in yourself interesting to </s><s>[INST] make you suggest creating a product that, uh, at least two more love than hate. [/INST] You're gonna want to love your neighbor because you're gonna make a fortune. I'd get there. That's why I'm on </s><s>[INST] board. That's why yuan said love is the answer. That's I think, uh, exactly what he meant. Okay, let's try something difficult. You've recorded episode steering into the iceberg on your common sense program that has started a lot of conversations. It's quite moving. It was quite haunting. I [/INST] made a lot of angry emails </s><s>[INST] really. Of course [/INST] I did something I haven't done in 30 years. I endorsed a political candidate from one of the two main parties and there were a lot of disillusioned people because of that. </s><s>[INST] I guess I didn't hear it as an endorsement. I just heard it as a, the similar flavor of conversations you have in, in hardcore history. It's almost a speaking about modern times in the same voice as you speak about when you talk about history. So it was just a a little bit of a haunting view of the world today. I know we were just wearing our Doom [/INST] Doom Master put that right back on our, you know, </s><s>[INST] the, uh, I like the term doom castor is there, is there? How do we get love to win? What's the way out of this? Is there some hopeful line that we can walk to a to avoid something? And I hate to use the terminology, but something that looks like a civil war, not necessarily a war of force, but a division to a level where it doesn't any longer feel like a United States of America with the emphasis on United. Is there a way out? [/INST] I read a book a while back, I want to say George Friedman. The street for a guy wrote it was something called The Next 100 Years, I think it was called. And I remember thinking um I didn't agree with any of it. And one of the things I think he said in the book was that the United States was going to break up. I'm going from memory here. He might not have said that at all, but something was stuck in my memory about that. I remember thinking, um, but I think some of the arguments were connected to the differences that we had and the fact that those differences are being exploited. So we talked about media earlier in the lack of truth and we have a media climate that is incentivized to take the wedges in our society and make them wider and there's no countervailing force to do the opposite or to help, you know? So there was a famous uh memo from a group called project for a new american century and they took it down. But the way back machine online still has it. And it happened before 9 11 spawned all kind of conspiracy theories because it was saying something to the effect of uh and I'm really paraphrasing here. But you know that the United States needs another Pearl Harbor type event because those galvanized a country that without those kinds of events periodically is naturally geared towards pulling itself apart. And it's those periodic events that act as the countervailing force that otherwise is not there. Um, if that's true, then we are naturally inclined towards pulling ourselves apart. So to have a media environment that makes money off widening those divisions, which we do. I mean, I was in talk radio and and it has those people, the people that used to scream at me because I wouldn't do it. But I mean, we would have these terrible conversations after every broadcast where I'd be in there with the program director and they're yelling at me about heat. Heat was the worthy create more heat. Well, what is heat right here? This division? Right? And they want the heat, not because their political, they're not republicans or democrats either there. We want listeners and we want engagement and involvement. And because of the constructs of the format, you don't have a lot of time to get it. So you can't have me giving you like on a podcast an hour and a half or two hours where we build a logical argument And you're with me the whole way your audience is changing every 15 minutes. So whatever points you make to create interest and intrigue and engagement have to be knee jerk right now. Things they told me once that the audience has to know where you stand on every single issue within five minutes of turning on your show. In other words, you have to be part of a of a linear set of political beliefs. So that if you feel a about subject a then you must feel de about subject D. And I don't even need to hear your opinion on it, because if you feel that way about a you're going to feel that way about D. This is a system that is designed to pull us apart for profit, but not because they want to pull us apart, right? It's a byproduct of the Prophet. That's one little example of a 50 examples in our society that work in that same fashion. So what that project for a new American century document was saying is that we're naturally inclined towards disunity and without things to occasionally ratchet the unity back up again. So that we can start from the baseline again and then pull ourselves apart till the next Pearl Harbor that you'll pull yourself apart, which I think was I think that's what the George Friedman book was saying that I disagreed with so much at the time. Um, so in answer to your question about civil wars, we can't have the same kind of civil war because we don't have a geographical division. That's as clear cut as the one we had before. Right? You have to basically north south line and some border states, it was set up for that kind of split. Now we're divided within communities, within families, within gerrymandered voting districts and precincts, right? So you can't disengage we're stuck with each other. So there's a civil war now, for lack of a better word, what it might seem like is the late 19 sixties, early 19 seventies where you had the bombings and you know, let's call it domestic terrorism and things like that because that that would seem to be something that once again, you don't even need a large chunk of the country. Pulling apart 10% of people who think it's the end. Times can do the damage. Just like we talked about terrorism before and a can of gas and a big lighter. I've lived in a bunch of places and I won't give anybody ideas where a can of gas and a big lighter would take 1000 houses down before. You could blink right? Um, that terrorist doesn't have to be from the Middle East doesn't have to have some sort of a fundamentalist religious agenda. It could just be somebody really piste off about the election results. So once again, if we're playing an odds game here, everybody has to behave for this to work right. Only a few people have to misbehave for this thing to go sideways and remember for every action there's an equal and opposite reaction. So you don't even have to have those people doing all these things, All they have to do is start retribution cycle. </s><s>[INST] And there's an escalation [/INST] and it go and it creates a momentum of its own, which leads fundamentally if you follow the chain of events down there to some form of dictatorial government as the only way to create stability, right? You want to destroy the republican, have a dictator. That's how you do. And there are parallels to Nazi Germany, the burning of the Reichstag, you know, blah, blah, blah. I'm the doom caster again. Well, </s><s>[INST] and some of it could be manufactured by those seeking authoritarian power. Like [/INST] The Reichstag fire was or the Polish soldiers that fired over the border before the invasion in 1939, </s><s>[INST] uh, to fight the Devil's Advocate with an angels advocate, I would say, just as our conversation about Ellen, it feels like individuals have power to unite us to be that force of unity. So, you mentioned the media, I think you're one of the great podcast, there's in history, joe Rogan is uh, like a long form, whatever it's not podcasting, it's actually whatever [/INST] the very infrequent is what it is, no matter what it is. </s><s>[INST] But the basic process of it is you go deep and you stay deep and the listener stays with you for a long time. So I'm just looking at the numbers like we're Almost three hours in and I from previous episodes, I can tell you that about 300,000 people are still listening to the sound of our voice three hours in. So usually 300-500,000 people listen and [/INST] they to regulations. By the way, that's wonderful, joe </s><s>[INST] Rogan is what, like 10 times that. And so he has power to unite. You have power to unite. There's a few people with voices that it feels like they have power to unite. Even if you if you quote unquote, endorse a candidate and so on, they're still, it feels to me that speaking of, I don't want to keep saying love, but it's love and maybe unity more practically speaking that like sanity that like respect for those you don't agree with or don't understand. So empathy. Well, just a few voices of those can help us avoid the really importantly, not avoid the singular events like you said, of somebody starting a fire and so on, but avoid the escalation of it. The preparedness of the populist to escalate those events to uh, to to turn a singular event and a single riot or shooting or like even something much more dramatic than that. To turn that into something that creates like ripples they grow as opposed to ripples that fade away and so like I would like to put responsibility on somebody like you and uh me in some small way and joe being cognizant of the fact that a lot of very destructive things might happen in november and a few voices can save us is the feeling I have not by saying who you should vote for or any of that kind of stuff, but really by being the, the voice of calm that like calms the seas from or whatever. The analogy is from boiling up because I truly am worried about this is the first time this year when I, I sometimes I somehow felt that the american project will go on forever when I came to this country, I just believed and I think I'm young but like you know, I have a dream of creating a company that will do a lot of good for the world and I thought that America is the beacon of hope for the world and the ideas of freedom, but also the idea of empowering companies that can do some good for the world. And I'm just worried about this America that filled me, a kid that came from, our family came from nothing and from, you know Russia as it was soviet union as it was to be able to do anything in this new country. I'm just worried about it and it feels like a few people can still keep this project going. Like people like Ellen people like joe uh is there, do you have a bit of that? Hope [/INST] I'm watching this experiment with social media right now. I don't even mean social media really expand that out to. Um I mean I feel like we're all guinea pigs right now watching, you know, I have two kids and just watching and there's a three year space between the two of them. One is 18, the other's 15 And just you know, in when I was a kid, a person who was 18 and 15 would not be that different, just three years difference, more maturity but their life experiences, you would easily classify those two people as being in the same generation now because of the speed of technological change, there is a vast difference between my 18 year old and my 15 year old and not in the maturity question, just in what apps they use, how they relate to each other, how they deal with their peers, their social skills, all those kinds of things where you turn around and go, this is uncharted territory we've never been here. So it's going to be interesting to see what effect that has on society now as that relates to your question. The most upsetting part about all that is reading how people treat each other online and you know, there's lots of theories about this? The fact that some of it is just for trolling laughs that some of it is just people are not interacting face to face so they feel free to treat each other that way. Um, and I of course I'm trying to figure out how, how if this is how we have always been as people, right? We've always been this way, but we've never had the means to post our feelings publicly about it or if the environment and the social media and everything else has provided a change and changed us into something else. Um, either way when one reads how we treat one another and the horrible things we say about one another online, which seems like it shouldn't be that big of deal. They're just words, but they have a cumulative effect. I mean when you uh I was reading um Megan Markle who I don't know a lot about because it's it's too much of the pop side of culture for me to pay a lot. But I read a story the other day where she was talking about the abuse she took online and how incredibly overwhelming it was and how many people were doing it. And you think to yourself, okay, this is something that people who were in positions of what you were discussing earlier never had to deal with. Let me ask you something. And boy, this is the ultimate doom caster thing of all time to say when you think of historical figures that push things like love and peace and um and and creating bridges between enemies when you think of how what happened to those people, first of all, they're very dangerous. Every society in the world has a better time, easier time dealing with violence and things like that than they do. Nonviolence. Nonviolence is really difficult for governments to deal with. For example, what happens to Gandhi and jesus and martin Luther king And you think about all those people, right? When they're that day, it's ironic, isn't it that these people who push for peaceful solutions are so often killed, but it's because they're effective and when they're killed, the effectiveness is diminished. Why are they killed? Because they're effective? And and the only way to stop them is to eliminate them because they're charismatic leaders who don't come around every day. And if you eliminate them from the scene, the odds are you're not going to get another one for a while. I guess what I'm saying is the very things you're talking about which would have the effect you think it would write, they would destabilize systems in a way that most of us would consider positive. But those systems have a way of protecting themselves, right? And and so I feel like history shows the history is pretty pessimistic I think by and large. Um if only because we can find so many examples that just sound passive, but I feel like people who are dangerous to the way things are tend to be </s><s>[INST] removed. Yes, but there's two things to say. I feel like you're right that history, I feel like the ripples that love leaves in history are less obvious detect are actually more transformational. Like [/INST] anyone can make a case about, I mean if you want to talk about the long term value of a jesus or Gandhi yes, those people's ripples are still affecting people today. I agree. </s><s>[INST] And that's you feel those ripples through the general improvement of the quality of life that we see and throughout the generations like you feel the ripples through the girl but I would even if that's not true not, I tend to believe that and by the way that the company that I'm working on is a competitor is exactly attacking this, which is a competitor to twitter, I think I can build a better twitter as a first step. [/INST] There's a long story in there. I think a three year old child could build and that this is not to denigrate, I'm sure yours will be better than, but twitter is so listen, facebook too, they're, they're really awful platforms for intellectual discussion and meaningful discussion, but when I'm on it, so let me just say I'm part of the problem, we're new </s><s>[INST] to this. So it's not, it wasn't obvious at the time how to do, it's now now a three year old can do. I tend to believe that we live in a time where the tools that people that are interested in providing love. Like the weapons of Love are much more powerful. So like the one nice thing about technology is that allows anyone to build a company that's more powerful than any government. So that could be very destructive. But it could be also very positive. And that's I tend to believe that somebody like Elon wants to do good for the world, Somebody like me and then you like me could have more power than anyone. Government two and by power, I mean the power to affect change, which is different from the [/INST] government and I don't mean to interrupt you but I'll forget my train of thought, you know what I mean? How do you deal with the fact that already governments who are afraid of this are walling off their own internet systems as a way to create firewalls simply to prevent you from doing what you're talking about. In other words, if you know there's an old line that if voting really changed anything, they'd never allow it. If if love through a modern day successor to twitter would really do what you wanted to do and this would destabilize governments. Do you think that governments would would take countermeasures to squash that love before it got too dangerous. There's several </s><s>[INST] answers. One first of all, I don't actually to push back on something you said earlier. I don't think love is as much of an enemy of the state As as one would think [/INST] different states have different views. </s><s>[INST] I I think the states want power and I don't always think that love is intention with power. Like I think and and and I think it's not just about love, it's about rationality is reason, it's empathy. All of those things. I don't necessarily think there always have to be by definition in conflict with each other. So that's one sense is I feel like basically you can trojan horse love into behind behind. Uh, but you have to be good at it. This is the thing is you have to be conscious of the way these states think so the fact that china bans certain services and so on, that means the companies weren't eloquent. Whoever the companies are, weren't actually good at infiltrating. Like I think isn't that a song like Love is a battlefield? I think [/INST] it's all a gap editorial. </s><s>[INST] Yeah. It's all a game and you have to be good at the game. And just like Ellen we said, you know, with Tesla and saving uh, the environment. I mean that's not just by getting on a stage and saying it's important to save the environment is by building a product that people can't help but love and then convincing Hollywood stars to love it. Like there's there's a game to be played. [/INST] Okay, so let me let me build on that because I think there's a way to see this. I think you're right. And so it has to do with a story about the 19 sixties, in the vast scheme of things. The 19 sixties looks like a revival of neo romantic ideas. Right? I had a buddy of mine several years, well, Two decades older than I was, who was in the 60s, went to the protest and all those kind of things, and we were talking about it and I was romanticizing it, and he said, don't romanticize, because let me tell you most of the people that went to those protests and did all those things, all they were, there was to meet girls and have a good time and, you know, it was it wasn't so but it became in vogue to have all in other words, let's talk about your empathy and love. You're never gonna, in my opinion, grab that great mass of people that are only in it for them, they're interested in whatever. But if meeting girls for a young teenage guy requires you to feign empathy, requires you to read deeper subjects because that's what people are into. You can almost as a silly way to be trendy, you can make maybe empathy trendy love trendy solutions that are the opposite of that. Um the kind of things that people inherently will not put up with, in other words, the possibility exists to change the zeitgeist and reoriented in a way that even if most of the people aren't serious about it. the results are the same. Does that make sense? Absolutely. Okay, so we found a meeting of the month. </s><s>[INST] Yeah, exactly. Creating creating incentives that and encourage the best and the most beautiful [/INST] aspects of nature. Will </s><s>[INST] it all boils down to meeting girls and boys? [/INST] Once again, you're getting to the bottom of the evolutionary motivations and you're always on safe ground when you do </s><s>[INST] that. This is a little difficult for me. I've, you know, and I'm sure it's actually difficult for you to listen to me, you say complimenting you, but it's difficult for both of us. Okay, So, but uh you know, you and I as I mentioned to you, I think I might have been friends for a long time. It's just been one way. So like everyone, it's two way, it's too right now. So like that's the beauty of podcasting, you know, I mean now just been fortunate enough with this particular podcast that I see it in people's eyes when they meet me that they've been friends with me for for a for a few years now and and we become fast friends actually after we start talking, but it's one way in the vet and now, first moment uh you know, like there's something about, especially hardcore history that, you know, I do some crazy challenges and running and stuff. I remember in particular Probably don't have time, one of my favorite episodes, the painful Tainment one. Some [/INST] people hate that episode </s><s>[INST] because it's too real. [/INST] Uh, it's my darkest one. We wanted to set a baseline. That's the baseline. </s><s>[INST] But I remember listening to that and when I ran 22 miles for me, that was a long distance and that's [/INST] entertainment, Right? </s><s>[INST] Yeah. And it just pulls you in and there's something so powerful about this particular creation that's bigger than you actually, that you've created. [/INST] It's kind of interesting. I think anything that is successful like that, like Dylan stuff to, it becomes bigger than you and that's, that's what you're hoping for, right? </s><s>[INST] Absolutely. Didn't mean to interrupt you [/INST] apologize. I guess </s><s>[INST] one question I have, if you like, look in the mirror, but you also look at me, what advice would you give to yourself and to me and two other podcasters, maybe to joe Rogan about this journey that we're on? I feel like it's something special. I'm not sure exactly what's happening, but it feels like podcasting is special. What advice? And I'm relatively new to it. What advice do you have for for people that are carrying this flame and traveling in this journey? [/INST] Well, I'm often asked for advice by new podcasters. People just starting out. And so I have sort of a tried and true list of dues and don't stand, but I don't have, um, advice or suggestions for you or for joe joe doesn't need anything from me, joe's figured it out, right? I mean he </s><s>[INST] hasn't yet. He's still confused kid curious about the world. [/INST] That's, but that's the genius of it. That's what makes it work, right? That's what, that's what Joe's brand is, right. Um, I guess what I'm saying is is by the time you reach the stage that you're at or joe's at or they don't need, they have figured this out. The people that sometimes need help our brand new people trying to figure out what do I do with my first show and how do I talk to them? And I've standard answers for that. But you found your niche. I mean, you don't need me to tell you what to do. As a matter of fact, I might ask you questions about how you do what you do, right? Well, </s><s>[INST] there's uh, I guess there's specific things like we were talking off line about monetization. That's a fascinating one. [/INST] Very difficult. Uh, as an independent </s><s>[INST] and uh, one of the things that joe is facing with, I don't know if you're paying attention, but he joined Spotify With $100 million exclusivity, that one, I don't give a damn about money personally, but I'm single. So, and I like like living in a shady place, so [/INST] I </s><s>[INST] enjoy, so I guess makes it easy [/INST] to get the freedom right. </s><s>[INST] Freedom materials is slave not [/INST] saving for anybody's college. </s><s>[INST] Exactly. Okay. So at that point, but I also, okay, maybe it's romanticization, but I feel like podcasting is pirate radio and when I first heard about Spotify partnering up with joe, I was like, you know Funk? The man I, I said, I I even I drafted a few tweets and so on. Just like attacking Spotify. Then I calmed myself down that you can't lock up this special thing we have. Uh, but then I realized that maybe that these are vehicles for just reaching more people and actually respecting podcast, there's more and so on. So that's what I mean by it's unclear what the journey is Because uh, you also serve as a beacon for now. There's like millions, one million plus podcasters. I wonder what the journey is. Do you have a sense? Um, are you romantic in the same kind of way in feeling that because you have a roots in radio to do you feel that podcasting is pirate radio Or is this Spotify thing one possible avenue. Are you nervous about Joe as a fan, as a friend of Joe or is this it's a good thing for us. [/INST] So my history of how I got involved in podcasting is interesting. I was in radio. Uh, and then I started a company back in the era where the dot com boom was happening and everybody was being bought up and it just seemed like a great idea, right? Started. Um, I, I did it with seven other six other people and the whole goal of the company was, and we had, we had to invent the term, I'm sure everybody, I mean, there's other places that invented it at the same time, but what we were pitching to investors was something called amateur content. This is before Youtube, before podcasting, before all this stuff and I, my job was to be the evangelist and I would go to these people and uh, and, and sing the praises of all the ways that amateur content was going to be great. And I never got a bite. And they all told me the same thing. This isn't gonna take off because anybody who's good is already going to be making money at this. And I kept saying, forget that we're talking about scale here. If you have millions of pieces of content being made every week, A small percentage is going to be good, no matter what, right, 16 year olds will know what other 16 year olds like. I kept pushing this nobody bit. But the podcast grew out of that because if you're talking about amateur content in 1999, well then you're already where, you know, you're ahead of the game in terms of, of not seeing where it's going to go financially, but seeing where it's going to go technologically. And so when we started the podcast in 2005 and it was the political one, not hardcore history, um, which was an outgrowth of the old radio show. Um we didn't have any financial um, ideas, we were simply trying to get a handle on the technology and how you distribute it to people and all that. And it was years later we tried to figure out, okay, how can we get enough money to just support us while we're doing this? And, and the cheap in the easy way was just to ask listeners to donate like PBS kind of model and that was, that was the original model. Um, so then once we started down that we figured out other models and this advertising thing and we sell the old shows and so all these became ways for us to support ourselves. Um, but as, as podcasting matured and as more operating systems developed and phones were developed and all these kinds of things, every one of those developments, which actually made it easier for people to get the podcast actually made it more complex to make money off of them. So while our audience was building the amount of time and effort we had to put into the monetization side began to skyrocket. So to get back to your Spotify question to use just one example, there's a lot of people who are doing similar things um, In this day and age, you know, we just sell MP three files and all you had to have was an MP three player is cheap and dirty. Now every time there's an os upgrade something breaks for us. So we're having, I mean my choices are at this point to start hiring staff, more staff, you know, people don't, and then be a human resources manager. I mean the pirate radio side of this was the pirate radio side of this because you didn't need anybody, but you know, you are you and another, I mean, you could just do this lean and mean and it's becoming hard to do it lean and mean now. So if somebody like a Spotify comes in and says, hey, um, we'll handle that stuff for you in the past, I would just say f off, we don't need you, I don't mind. And I definitely am not making what we could make on this, but what we would have to do to make that is onerous to me, but it's becoming onerous to me day to day anyway. And so if somebody were to come in and say, hey, we'll pick that up for you, we will not interfere with your content at all. We won't, and in my case, you can't say we need to show a month because that ain't happening, right? So, I mean, everybody's, everybody's uh design is different, right? So it doesn't, you know, there's not one size fits all, but I guess as a long time pirate podcaster, um, there are, you know, we've been looking to partner with people, but nobody is right for us to partner with. I mean, so, so I'm always looking for ways to take that side of it off my plate because I'm not interested in that side. All I wanna do is the shows and they, you know, it's really at this point you shouldn't call yourself an artist because you know, that's something to be decided by others. But I mean what we're trying to do art and there's something very satisfying in that, but the part that I can't stand is the increasing amount of time the monetization question takes upon us. And so there's a case to be made, I guess is what I'm saying that if a partnership with some outside firm enhances your ability to do the art without dis enhancing your ability to do the art, it's um, the word I'm looking for here is it's um, it's enticing uh, I don't like big companies. Um, so I'm afraid of, of whatever strings might come with that. And if I'm joe Rogan and I'm talking about subjects that can make company public companies, you know, a little nervous. Um, I would certainly be careful. But at the same time, people who are not in this game don't understand the problems that literally, I mean, just all the operating systems, all the podcasters every time some new podcaster comes out makes it easier to get the podcast. That's something we have to account for on the back end and I'm not exactly the technological wizard of all time. So, um, I think it is maybe maybe the short answer is is that as the medium develops, it's becoming something that you have to consider not because you want to sell out, but because you want to keep going and it's becoming harder and harder to be pirate. Like in this environment. </s><s>[INST] The thing that convinced me, especially inside Spotify is that they understand, so if you walk into this whole thing with some skepticism as you're saying a big companies, then then it works because Spotify understands the magic that makes podcasting or they appear to in part at least they understand enough to respect joe Rogan and despite what I don't know if you, uh, so there's the internet and there's people with opinions on the internet. Yes. And they have opinions about joe and Spotify, but the reality is there's two things in private conversation with joe and in general there's, there's two important things. One, Spotify literally doesn't tell joe anything like all the people that think they Spotify somehow pushing joe in this direction of [/INST] that didn't insist upon that </s><s>[INST] it's in the contract, but also, you know, companies have a way of, even with the country to be, you know, marketing people, hey, I know we're not forcing. [/INST] Yeah, yeah, yeah, I hate that. </s><s>[INST] But with what you and joe are the same. And Spotify smart enough not to send a single email of that kind that's really smart and they leave, they leave them be there is meetings inside Spotify that like people about people complain. But those meetings never reached joe that, that never, that's a company stuff. And the idea that that Spotify is different than pirate radio. The difficult thing about podcasting is nobody gives a damn about your podcast. You're alone in this. I mean there's fans and stuff but nobody, nobody's [/INST] looking out for you. Yeah, </s><s>[INST] and the nice thing about Spotify is they want joe to joe's podcast to succeed even more. That's what joe talked about is that's the difference between Youtube and Spotify. Spotify wants to be the Netflix of podcasting and they like what Netflix does is they they, they don't want to control you in any way, but they want to create a platform where you can flourish [/INST] because your interests are aligned. The interests. Let me bring up, let me bring up something that let's make a distinction because not all companies who do this are the same and you brought up Youtube and Spotify, but to me, Youtube is at least more like Spotify than some of these smaller, the term is walled garden. Right? You've heard the term walled garden. Okay, so um I've been around podcasting so long now that I've seen rounds of consolidation over the years and they come in waves and then all of a sudden, so you'll get and I'm not going to mention any names, but up until recently the consolidation was happening with relatively small firms compared to people like Spotify. And the problem was, is that by deciding to consolidate your materials in a walled garden, you are walling yourself off from audience, right? Um so your choices, I'm gonna accept this amount of money from this company, but the loss is going to be a large chunk of my audience and that's a catch 22 because you're negotiating power with that company is based on your audience size. So signing up with them diminishes your audience size, You lose negotiating power, but when you get to the level of the Spotify to just pick them out, there's other players, but you brought up Spotify specifically these are people who can potentially potentially enhance your audience over time. And so the risk to you is lower because if you decide in a year or two, whatever the licensing agreements term is that you're done with them and you want to leave instead of how you would have been with some of these smaller walled gardens where you're walking away with a fraction of the audience you walked in with, you have the potential to walk out with whatever you got in the original deal plus a larger audience because their algorithms and everything are designed to push people to your content if they think you'd like. So it takes away some of the downside risk which which alleviates and if you can write an agreement like joe Rogan, I mean where you've protected your your freedom to, to put the content of the way you want. So if some of the downside risk is mitigated and if you eliminate the problem of trying to monetize and stay up with the latest tech, then it might be worth it. You know, I'm scared of things like that, but at the same time I'm trying to not be an idiot about it and I can be an idiot about it and when you've been doing it as independently for as long as I have, the inertia of that has a force all its own. But I'm I'm inhibited enough in what I'm trying to do on this other end that it's opened me at least listening to people. Um, but listen, at the same time, I love my audience and it sounds like a cliche, but they're literally the reason I'm here. So I want to make sure that whatever I do, if I can, is in keeping with A relationship that I've developed with these people over 15 years. Um, but like you said, no matter what you do, you are because see here's the thing, if you don't sign up with one of those companies to make it easier for them to get your stuff on this hand, they might yell at you for how difficult it is because the new, uh, new new operating system just updated, you can't get yourself. So either way you're opening yourself up to ridicule at this point, all of that makes it easier to go well if the right deal came along and we weren't screwing me and they weren't screwing my audience and blood was um, you know, I mean, again in this business, when you're talking about cutting edge technology, that is ever changing and as you said, a million podcasts and growing, I think you have to try to maintain flexibility and especially if they can mitigate the downside risk. I think you have to, I think you'd be an idiot to not at least try to stay up on the current trends and look, I'm watching joe, I'm going, okay, let's see how it goes for joe. You know, I mean, if, if he's like, this is terrible, I'm getting out of this, you go, okay, Those people are, you know, so Jos, jos put himself out as a guinea pig and I, and the rest of us, guinea pigs appreciate </s><s>[INST] as a huge as a fan of your shows and as a fan of netflix. The people there, I think I can speak for like millions of people in hope that the hardcore history comes to netflix or Spotify becomes the netflix of podcasting. That to Spotify, there's something at, it's best that they bring out the you said artists, so I can say it is, they bring out the best out of the artists, they removed some of the headache and somehow like they put at their best netflix, for example, is able to enforce and find the beauty and the power and the creations that you make even better than you like. They don't interfere with the creations, but they somehow, it's a branding thing probably to [/INST] interfering would be, that would be a no go from. That's right. Absolutely. That can't, that can't </s><s>[INST] help. But that's why netflix is masterful. They seem to not interfere with the talent as opposed to I could throw other people under the bus. [/INST] Like I'm a lot of places </s><s>[INST] under the bus that could be thrown. Absolutely. So I would love, I know there's probably people screaming yes right now in terms of hardcore history on netflix would be awesome. Um, I don't love asking this question, but it's asked probably the most popular question that's unanswerable. So let me try to ask it in a way that you would actually answer it, which is of course you said you don't release shows very often. And uh, the question is the requests and the questions is, well, can you tell dan to do one on the civil wars, Can you tell dan to do one on the polling Bonaparte? Can you can tell him to do one? You know every, every topic and you've spoken to this actually, your answer about the civil war is quite [/INST] interesting. I didn't know you knew what my answer, but the civil war </s><s>[INST] that you don't as a military historian you enjoy in particular when there's differences in the army as a contrast contrasts with the civil war, which like blew my mind when I heard you say is, you know, it's there's not an interesting, deep, intricate contrast between the two opposing [/INST] the roman civil wars which legionaries against legendary </s><s>[INST] is. And you've also said that you kind of, the shows you work on are ones where you have some roots of fundamental understanding about that period. And, and so like when you work on the show, it's basically like pulling at those strings further and like refreshing your mind and [/INST] learning, definitely done the research. </s><s>[INST] Wow, these are words [/INST] out of my mouth. Yeah, you're right. </s><s>[INST] So, but is there something like, like shower thoughts on reddit? Uh, is there some ideas that are like lingering in your head about possible future episodes? Is there things that whether you uh not committing to anything, but whether you're going to do it or not, is there something that's like, makes you think that would be interesting to uh, to pull at that thread a little bit? [/INST] Oh yeah, we have things we keep in our back pocket for later. So, uh, blueprint for Armageddon, the first World War series we did. That was in my back pocket the whole time. And when the centennial of the war happened, it just seemed to be the likely time to bring out what was that </s><s>[INST] was a hell of a series. That's probably one of my favorites, My [/INST] rear end man, </s><s>[INST] I have to take psychologically, I mean, [/INST] You know when you get to these, I think I'm guessing here, I think it's 26 hours. All pieces together. Think about and, and we don't do scripts, it's improvised. So think about what 20 I had somebody write on Twitter just yesterday saying um he said something like I'm not seeing the dedication here, you're only getting 2.5 shows out of here. And I wanted to say, man, you have no idea what the only people who understand really are other history podcasters and even they don't generally do 26 hours. You know, that was a two year endeavor. Um as I said, the first show we ever did was like 15 minutes. I could crank out one of those a month, but when you're doing, I mean the last show we did on the fall of the roman republic was 5.5 hours, that's a book, Right? Um and it was part six or something. So I mean you just do the math. Um and it </s><s>[INST] felt like you were sorry to interrupt on, on World War One. It felt like you were emotionally pulled in to it. Like it felt taxing. [/INST] I was gonna say that's a good thing though because you know, and I think we said during the show, that was the feeling that the people at the time happened. I think in at one point we said that this is starting to seem gruesomely repetitive now, you know, how the people at the time felt. So in other words that had any sort of inadvertently, because when you improvise a show, some of these things are inadvertent, but it had inadvertently created the right climate for having a sense of empathy with the storyline. And to me that those are the serendipitous moments that make this art and not uh some sort of paint by the numbers kind of endeavor, you know, And and that's to me, that wouldn't have happened had we scripted it out? </s><s>[INST] So it's mostly you just bring the tools of knowledge to the table and then in large part improvised, like, the actual warding. [/INST] I always say we make it like, they made things like spinal tap and some of those other things where um the material. So, I do have notes about things like, on page 4, 27 of this book, you have this quote, so that I know Aha, I'm at the point where I can drop that in. Um and sometimes I'll write notes saying, here's where you left off yesterday. So I remember, um but in the improvisation, you end up throwing a lot out. And so, um like, like, but it allows us to go off on tangents, like we'll try things like, I'll sit there and go, I wonder what this would sound like, and I'll spend two days going down that road and then I'll listen to and go, doesn't work. But that's, you know, like writers do this all the time. It's called Killing Your Babies, right? You can't get, but people go, so this guy goes, I'm not seeing the dedication. He has no idea how many things were throwing out. I did an hour and a half. I had an hour and a half into the current show about two months ago and I listened to it. I just went, you know what? It's not right, boom, out the window. There goes six weeks of work, Right? But here's the problem. You trust your sorry to interrupt. You. Trust your judgment on that. No, no. But, but here's, here's the, here's the thing. Um, our show is a little different than other people's joe Rogan called it evergreen content in other words. Uh, My Political Show is like a car you buy and the minute you drive it off the lot it loses half its value because it's not current anymore. These shows are just as good or just as bad. Five years from now as they are when we do. Although the standards on the internet changed when I listen to my old shows, I cringe sometimes because the standards are so much higher now. But um, when you're creating evergreen content, you have to audiences to worry about, you have the audience that's waiting for the next show and they've already heard the other ones and they're impatient and they're telling you on twitter where is it? But you have show the show is also for people five years from now who haven't discovered it yet and you don't care a wit for how long it took because they're going to be able to download the whole and all they care about is quality. And so what I always tell new podcasters is they always say I read all these things that it's very important to have a good release schedule. Well it's not more important than putting out a good piece of work and the audience will forgive me if it takes too long. But it's really good when you get it. They will not forgive me if I rush it to get it out on time and it's a piece of crap. So for us and this is why when you brought up a Spotify deal or anything else they can't interfere with this at all. Because my my job here as far as I'm concerned is quality. And everything else goes by the wayside. Because the only thing people care about long term. The only thing that gives you longevity is how good is it? Right? How good is that book? If you read J. R. R. Tolkien's work tomorrow, you don't care how long it took him to write it. All. You care is how good is this today And that's what we try to think too and I feel like if it's good if it's really good, everything else falls into place and takes care of itself. Um, </s><s>[INST] although sometimes to push back, sorry to interrupt, [/INST] I've done it to you 1000 times. So you can get me back. </s><s>[INST] Sometimes the deadline you, you know, some of the greatest, like movies and books have been, you think about like dusty Sk I forget which one knows from underground or something. He needed the money. So he had to write it real quick. Sometimes the deadline creates is powerful at taking a creative mind of an artist and just like slapping it around to force some of the good stuff out. Now. The problem with history of course, is there's there's different definitions of good, um, that like, it's not just about what you talk about, which is the storytelling, the richness of the storytelling. And I'm sure you're, you know, again not to compliment you too much, but you're one of the great storytellers of our time. That, that I'm sure if you put in a jail cell and forced at a, like somebody point a gun at you, you could tell one hell of a good story, but you still need the facts of history or not necessarily the facts, but you know, like making sure you painting the right full picture not perfectly [/INST] right. That's what I meant about the audience doesn't understand what a history podcast, you can't just riff and be wrong. So let me let me both both oppose what you just said and back up what you just said? So I have a book that I wrote, right and uh in a book you have a hard deadline, right? So harper Collins had a hard deadline on that book. So when I released it I was mad because I would have worked on it a lot longer, which is my style, right, get it right. But we had a chapter in that book entitled Pandemic Prologue question mark, and it was the book about the part about the black death in the 1918 flu and all that kind of stuff. And and I was just doing an interview with a spanish journalist this morning who said, did you ever think how lucky you got on that on that? You know? And first of all, lucky on a pandemic, it strikes you. But had I had my druthers, I would have kept that book working in my study for months more and the pandemic would have happened. And that episode that would have looked like a chapter I wrote after the fact I would have to rewrite the whole thing, it would've been. So that argues for for what you said at the same time, I I would have spent months more working on it because to me it didn't look the way I wanted it to look yet, you know, </s><s>[INST] can you drop a hint of the things that you're keeping on the shelves, [/INST] the alexander, the great podcast, I've talked around, I talked to somebody today said, do you know that the very first word in your very first podcast in the title? The very first thing that anybody ever saw with hardcore history is the, is the word alexander because the show is entitled Alexandre versus Hitler. I have talked around the career, I've done show after I talked about his mother in one episode, I talked about the funeral games after his death. I've talked around this, I've specifically left this giant alexandria in size hole in the middle because we're going to do that show one day and I'm going to lovingly enjoy talking about this crazily interesting figure of alexander the Great, so that's one of the ones that's on the back pocket list. And what we try to do is whenever this we're doing um Second World War in Asia and the pacific Now, I'm on part five, whenever the heck we finish this, the tendency is to then pick a very different period because we've had it and the audience has had it. Um so it's time. So, um I will eventually get to the alexander saga. </s><s>[INST] What about just one last kind of a little part of this is what about the other half of that first 10 minute, 15 minute episode, which is so you've done quite a bit about the World War, you've done quite a bit about Germany will you ever think about doing Hitler and the man, [/INST] it's funny because uh I talked earlier about how I don't like to go back to the old shows because our standards have changed so much with a long time ago. One of my standards for not getting five hour podcast done or or not getting too deeply into them was to flit around the interesting points, but we didn't realize we were going to get an audience that wanted the actual history. We thought we could just go with assume the audience knew the details and just talk about the weird stuff that only makes up one part of the show now. So we did a show called Nazi Tidbits and it was just little things about, you know, it's totally out of date now, like, you know, you can still buy them, but they are out of date um where we dealt a little with it. Uh you know, it would be interesting, but I'll give you another example, I mean history is not stagnant as you know, uh and we had talked about Stalin earlier and ghosts of the Austrian was done years ago and people will write me from Russia now and say, well your portrayal of Stalin is totally out of out of uh it's outdated because there's all this new stuff from the former soviet union and you do you turn around and go, okay, um there, right, And so when you talk about Hitler, it's very interesting to think about how I would do a Hitler show today versus how I did 1 10 years ago, um and you would think, well, what's new? I mean, it happened so long, but there's lots of new stuff and there's lots of new scholarship and and so, um yeah, I would think that would be an interesting one to do someday. I haven't thought about that, that's not in the back pocket, but uh but yeah, that'd be interesting. </s><s>[INST] I have a disproportionate amount of power because trapped you somehow in the room and [/INST] thereby </s><s>[INST] during the pandemic. So, like, my hope will be stuck in your head, but after alexander the Great, which would be an amazing podcast, I, I hope you do give a return to Hitler, The Rise and Fall of the Third Reich which to me, uh really [/INST] temporary book, basically. Yeah, </s><s>[INST] and I Exactly, is by a person who was there. Yeah, I I really loved that study of the Man of Hitler, and I would love to hear your the study of certain aspects of it, and perhaps even an episode that's, like more focus on a very particular period. I just feel like you can uh tell a story that it's funny, Hitler is one of the most studied people, and I still feel like this, all the stories, or most of the stories haven't [/INST] been told, Oh, and there's listen, I've got three books at home, I'm on all the publishers lists now, and they just the young Hitler, there's this Hitler, there's that, I mean, I've been reading these books and I've read about Hitler, I read The Rise and Fall of the Third Reich my mother thought I needed to go to a psychologist because I read it when I was six and she said there's something wrong with the boy and but she was </s><s>[INST] absolutely right, [/INST] but but you would think that that's something like that is pretty established fact. And yet there's new stuff coming out all the time. And needless to say, Germany has been investigating this guy forever and sometimes it takes years to get the translations. I took five years of german in school, I can't read any of it. So, um so I mean, and, and and he is, when you talk about fascinating figures, he's so, the whole thing is so twisted, lee weird. Um there was a, it came out a couple of years ago, somebody found a tape of him talking to uh General, I want to say it was General, um the Finnish General Manor home, Right? And and he's just in a very normal conversation of, of the sort we're having now and you know, the Hitler tape when you hear normally is ranting and raving and but this was a very sedate and I wish I had understood the german well enough to really get a feel because I was reading what Germans said, They said, wow, you can really hear the southern accent, you know, little things that only a native speaker would hear. And I remember thinking this is such a different side of this twisted character and you would think you would always, you would think that this was information that was out in, in, in in in the rise and fall of the third Reich there, but it wasn't. And so this, this, this is a goes along with that stuff about new stuff coming out all the time, alexander, new stuff coming out all the time really well, at least interpretations rather than factual data </s><s>[INST] and those color your, that those give depth to your understanding. [/INST] Yes, you and you want that because the historian biography, people, people love that. And that was a byproduct of my lack of credentials where we thought we're going to bring in um the historians and we call them audio footnotes right away for me to say, listen, I'm not a historian, but I'll quote this guy who is so you can trust him. But then we would quote other people who had different views and people didn't realize that that if they're not history majors, that historians don't always agree on this stuff and that they have disagreements and they loved that. So, so I I love the fact that there's more stuff out there because it allows us to then bring in um other points of view and sort of maybe three dimensional eyes or flesh out the story a little bit more </s><s>[INST] To ask questions. One really simple one, absurdly ridiculous and perhaps also simple first, who has been in a surreal, [/INST] I don't even know what you're talking about </s><s>[INST] very well. [/INST] How's that for an answer? Like asking me is harvey the white rabbit real. I don't know, there's carrots all around the production room, but I don't know what that means. </s><s>[INST] Well, a lot of people demanded that I prove I somehow figure out a way to prove the existence. [/INST] I said he was real. People would say no, he's not. And if I said he was if he wasn't real, they would say yes, he is. So it's a santa claus, easter bunny kind of vibe there. </s><s>[INST] I mean, what is real? Anyway, [/INST] that's exactly what I told him. It </s><s>[INST] exists. Okay. The most absurd question, I'm very sorry, very sorry. But then again, I'm not. What what what's the meaning of it all? You you study history of human history, Have you been able to make sense of why the hell we're here on this spinning rock? What does that even even make sense? What's the meaning of life? [/INST] What I look at some times that I find interesting is certain consistencies that we have over time, history doesn't repeat, but it has a constant and the constant is us now we change. I mentioned earlier the wickedly weird time we live in with what social media is doing to us as guinea pigs And that's a new element, But we're still people who are motivated by love, hate, greed, envy sex. I mean all these things that would have connected us with the ancients, right? That's the part that always makes history sound like it rhymes, you know? Um, and when you put the constant, the human element and you mix it with systems that are similar. So one of the reasons that the ancient roman republic is something that people .2 all the time. Um, as a, something that seems like we're repeating history because you have the two cons, you have humans just like you had then and you have a system that resembles the one we have here. So you throw the constant in with a system that is somewhat similar and you begin to see things that look like they rhyme a little. So for me, I'm always trying to figure out more about us. And when you show us in uh 500 years ago in Asia And 800 years ago in Africa, and you look at all these different places that you put the Guinea Pig in and you watch how the Guinea Pig responds to the different stimuli and challenges. I feel like it helps me flush out a little bit more who we are in the long timeline, not who we are today specifically, but who we've always been. Um, it's a personal quest. It's not meant to educate anybody else. It's, it's something that fascinates me. </s><s>[INST] Do you think there's uh in that common humanity throughout history of the guinea pig, is there a why underneath it all, or is it somehow like it feels like it's an experiment of some sort, [/INST] Oh, now you're into it, Elon musk. And I talked about this, the simulation thing, right? Nicb Ostrom, Sure, yeah, the idea that there's some, some kid and were the equivalent of an aliens and farm, you know, uh and we hope he doesn't throw a tarantula in just to see what happens. Um I think the wise elude us, and I think that what makes philosophy and religion and those sorts of things so interesting is that they grapple with the wise. Um but I'm not wise enough to to uh propose a theory myself, but I'm interested enough to read all the other ones out there. So um uh let's put it this way, I don't think there's any definitive y that's been agreed upon, but the various theories are fascinating. </s><s>[INST] Yeah, whatever it is, whoever the kid is that created this thing, the the ant farms kind of interesting [/INST] so far, a little bit, a little bit twisted and perverted in sadistic man, </s><s>[INST] that's what makes it fun, I think. But then again, that's the Russian perspective, [/INST] I was just gonna say </s><s>[INST] it [/INST] is the Russian perspective a little bit, what makes the Russians Russian history one day, I'll do some Russian history I took in college, Oh, that's the ant farm baby. That's an ant farm with a very, very frustrated young uh teenage alien kid </s><s>[INST] dan. I can't say I've already complimented you way too much. I'm a huge fan. This has been an incredible conversation. It's a huge gift. Your, your gift of humanity. I hope [/INST] you cut you often. Just say you've done a wonderful job. This has been fun for me. The questions and more importantly, the questions can come from anybody. The counter statements, your responses have been wonderful. You made this a very fun intellectual discussion for me. Thank you. </s><s>[INST] Let me have the last word and say, I agree with Ellen and despite the doom castor say that I think we've concluded definitively and you don't get a chance to respond that love is in fact the answer and the way forward. So thanks so much dan. Thank you for having me. Thanks for listening to this conversation with dan Carlin and thank you to our sponsors, athletic greens, the only one drink that I start every day with to cover all my nutritional bases, simply safe home security company. I used to monitor and protect my apartment magic spoon, low carb keto friendly cereal that I think is delicious and finally cash up the app. I used to send my need of friends for food and drinks, please check out these sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe on Youtube, review it with five stars on Apple podcast. Follow on Spotify, Support on Patreon. I'll connect with me on twitter Elex Friedman, and now let me leave you with some words from dan Carlin Wisdom requires a flexible mind. Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] been educated on, that just their whole life revolves around. Michael, you don't bring up Ayn Rand that much in conversation except as kind of references every once in a while as part of the humor of just the general flow and the music of the way you like to talk. Well, why do you think you don't integrate her into your philosophy when you're like explaining ideas and all those kinds of things? [/INST] Like why is she not, you know, a popular reference point for discussion of ideas? Because I don't know if everyone's going to agree with or can agree with me. I think for a certain percentage of the population, actually I talked to someone from the Ayn Rand institute, I forgot his name, Older Guy with Glasses, and he didn't disagree with me. He said, this is changing. I said, I think for a certain percentage of the population who are uninformed about her work, higher than 10%, less than 50%, you mentioned Ayn Rand, they have been trained to think this is identical to Scientology. So as soon as her name comes up, it's like, okay, I'm out the door. I'm not going to have anything to do with this. And everyone who follows her is a crazy person. That's one thing that has happened. Another thing is Rand in her personality was very aggressive and antagonistic. She was for a long time the lone voice in the wilderness being like, this isn't like one of her big adversaries in a certain sense is Milton Friedman. And she really hated how Milton Friedman was like, oh, you know, having rent control is inefficient. And she's like, inefficient. We're talking about mass homelessness and people dying. And you're talking about this, like what color tie goes with this color shirt? And in fact, it's hilarious. There was an organization called the Foundation for Economic Education Fee. Leonard Reed was the head of this. And there were a series of letters and she was helping him. She was much more philosophically grounded in a certain context than he was. And there was an essay, a pamphlet that he published called Roofs or Ceilings. It was co-written by Milton Friedman, later Nobel prize winner, and George Stigler, also later Nobel prize winner. And basically the argument was, well, if the government controls all housing, how's that going to work out? And she's sitting there and she's typing in all caps. So, you know, she's holding up this shift key and doing this on a typewriter and being like how, and you can imagine her app with her cigarette holder, apoplectic, being like, how is an organization ostensibly devoted to free enterprise discussing this Stalinist idea in the most casual of terms? She's like, have I taught you not? And what's amazing is so at fee, they only have her letters because she sent them to read the Ayn Rand Institute must have Leonard Reed's letters. I was able to, knowing Rand enough, predict exactly what the conversation would go like because he also did something she didn't approve of, which is he asked other people for feedback on her work. And she goes, I gave this to you to read. Who are you shopping around to some jerk that I don't, I need their approval. What are you doing? So it was a very interesting situation. But so that's one issue. I remember this is quite honest. I remember this is Ayn Rand when she's here. She was young. She wasn't that young. Well, I mean, it's before Ashleigh Shropp. It was before at left. So it's before she's super famous and before this is the fan heads being published. But she's trying to work with others and they're disappointing her left and right. She wasn't that young. She was in the 40s. And also when you are a, what she takes away from bad people is you have these kids, right? And you're going to sit down with them and they're going to be like, yeah, I'm going to take your guns. I'm going to lock you in your house. I'm going to take 60% of your income and all this other stuff. And they might up to reading Rand, they might sit down and have a discussion. And Rand goes, hey, you know what? You didn't have to give them an answer. You could say, go to hell. We're not having this conversation and you have no right to one second of my life. And this is not a legitimate opener. This is a declaration of war. This isn't like, it's not like if I sit down with you, I'm like, hey, Ron, here are my plans for your wife. Go to hell. This isn't a conversation we're having. Oh, I'm going to make you unsafe in your house. What? This is not a discussion. So what happens is these people who five minutes ago were able to have a debate with this kid because people read Rand when they're young often. And now that kid is like, yeah, I'm not even talking to you. It's her fault. Whereas in reality, it's that person's fault because that person had no right, although they've been trained to the contrary of our culture, to believe, yeah, I'm going to sit down and we're just going to equally have a discussion over your own life. And you have one vote and I have one vote and we're going to, oh, Lex has a vote and that's how it's going to be. And Rand's not having it. So I think those are two issues. And there's some other things which I don't need to get into, but one of the things that Rand said consisting of her life is that her philosophy is an integrated whole, right? So to be an objectivist isn't just like, I like Atlas Shrugged. It means I accept objectivism as a totality. Since I do not, I think it is proper to be respectful to her wishes and not constantly be, especially given that I have somewhat of a platform to be like, Ayn Rand, Ayn Rand, because I don't think Ayn Rand would have liked it if I was talking about Ayn Rand this much. </s>
<s>[INST] But you love the idea of being an actor like who you mentioned john candy and uh playing planes and automobiles, It's one of my favorite movies. This is one of yours, What do you think that makes that movie work? What, what do you what? [/INST] Um </s><s>[INST] and when you, when you talk about enjoying that movie, do you enjoy just the raw comedy or do you enjoy like the friendship and and the love that's there, even though on the surface it doesn't make any sense that there should be a friendship there. [/INST] I mean that's such an important element to that film. But uh, you know, as a kid, I just loved the comedy and then it's been a nostalgic favorite of mine, like it's my favorite movie. But it's also uh it's just legit my favorite movie because as you get older and you start watching it, you realize it's what it's what john Hughes is the filmmaker and what john Candy particularly and but also steve martin are doing in the film that makes it such a work of art, which is loneliness is there in every moment of that film and john candy is he embodies Del Griffith, his character in the film. He Del Griffith is a lonely guy and john candy, but but Del Griffith is also a very friendly guy and and a shower curtain ring salesman and knows everybody in the midwest and runs around to motels and has meaningful conversations with the guy evening gus, you know, whoever he's talking to. Um but there's loneliness there all the time and uh you know, this is a character that these, the film is filled with loneliness and it's not until, you know, the second last scene when he's at the train station. Del what are you doing here? You thought, I thought you were going home, what are you doing here? Um That's a very good neal neal page from the movie. Thank you. Uh That's when you realize how lonely cheers, that's when you realize how lonely is and I think that's the element from the film that I mean look, you know, nowadays, I feel like I've been saying this for a long time, but john candy would have won an Academy Award hands down for that film. It's just, they didn't do that with comedies back </s><s>[INST] then. You know the [/INST] year after that movie came out with fish called wanda. Yeah. </s><s>[INST] And then it's, I mean still comedies don't get respected enough Robin Williams. He got I guess he got an Oscar for [/INST] good, </s><s>[INST] Will hunting. Um jim Carey. Did he ever get an Oscar? [/INST] I don't know. I don't believe </s><s>[INST] so. Yeah, they don't get you don't but that's not even if he did, you wouldn't be for comedies. It's just I mean there's some things that are um planes, trains and honor. Maybe would you even put that as a calm? I guess it's a [/INST] comedy. There's </s><s>[INST] a there's a loneliness and depth that permeates the whole movie that ultimately and it's a happy ending which is hard to kinda, [/INST] it's a happy ending. Only because in the last moment of the movie, john candy puts on a brave face even when he's got no one and he's there seeing Neil pages, entire family on thanksgiving and he forces a smile which is the last literally the last frame of the movie and I've said before, if you're not reduced to just a sobbing pile of meat at the end of the movie then you are not human. Um Yeah, it's it's it is a happy ending. It's a happy ending even though it's a it's a sad, </s><s>[INST] so [/INST] much character, </s><s>[INST] loneliness in the world. I was just in Vegas I went to a diner like four a.m. Five A. M. And there's the waitresses empty as a waitress that was the sweetest, kindest human being kept calling me sweetheart and all that kind of stuff hon and then after I ate, she sat down and just talk to me a little bit. It was because there's nobody nobody there and it was just so much sadness in her eyes. I don't know. But also so much love like that sweetheart. That I mean it reminds me kind of um of john candy performance because at first, because I was like reading pretty dark uh book about Hitler. Uh so I was a little bit frustrated that she kept talking to me because it was like, it was it was almost like uh the same way that john Kenney's it's annoying a little bit, right? But then very quickly I opened up to like, oh, there's a there's a kind human being and there's like that human connection superseded everything else. And I don't know, it was just beautiful. And I think john Candy captures that really well, which is like the connection with other human beings. Sometimes we pull away from that because we have a busy life full of stuff to do. As um steve martin's character characterized. He's like a marketing execs or something like that. But if you just pause and notice others, you can, you can really discover beautiful people, [/INST] totally, totally everyone's got, I mean, everyone's got their their story and you know, Candy is a person I've never met the man. Uh but he's the kind of guy that, you know, he could, he could just walk up to back in the day. I would imagine he could walk up to just about any house at least in Canada knock on the door and you'd invite him in for dinner, you know what I mean? So yeah, it's a, it's a that, you know, as you're talking about, you know, putting a book down and talking to someone for a while, even though you'd really like to read your book, it's, it's like, it's that sort of thing that candy's character in the movie sort of does that like johnny Appleseed, just you realize he's just going around making people smile, you know, and, and Neil pages hanging with this guy so frustrated. He's just a, he's so exhausting and his big underwear in the sink at the hotel and everything, and by the end of it, he loves this guy, you know, so it's a good and a bad thing that you have didn't take that waitress with you on a trip, maybe road trip up to reno </s>
<s>[INST] So you're not trying to be somebody else I guess. Yeah. Just for having done like podcasts and lecture and that helps. I've embarrassed already done some of the work of the stand ups do, which is embarrassed yourself in front of others for prolonged periods of time. Yes, Yeah, so I've done that without actually developing the funny, but maybe the funny just is not that difficult to develop. Um No, it's super difficult of course, but I mean maybe the essential work of a stand up comedian is just the embarrassment of like finding who you [/INST] are. Yeah, that's a part of it for sure. You know, in the beginning you're like water bottle, What's funny about water bottle? I'm a funny guy, I can make this funny but that ain't, that's not it. You know, it's it's your ship, your ship, like your dark stuff for me, I tend to gravitate towards dark, but in a weird way where you know, people will say like, hey don't objectify women, but then they go Caitlyn Jenner is beautiful and you're like, well wait, I know something's off here, why can you objectify her? But not the supermodel. So what's going on there and I like to play with that. So I have this joke where I say Caitlyn Jenner? Oh, oh, women go Caitlyn Jenner is beautiful, beautiful woman. I go, well you look like her and they go fuck you and you're like, there's a lot of truth there but I like exploring that kind of, oh you're trying to get one over on me or your lying to yourself or what are we doing here? And I like, I like that kind of comedy. I don't see color. Well I'm black. No, you're not. You know, that's fun because you're you're lying. </s><s>[INST] Uh yeah, okay, so like big time comedians. It's just yourself. Don't like to think of yourself in this way. But yeah, this is like where you overfill philosophies comedy. But yeah, definitely. It seems like comedians [/INST] don't say important, nothing worse than a comedian who thinks they're important. </s><s>[INST] Yeah. So I was going, I was trying to find as I was trying to say these words, every realized how cliche it is and how interesting it is. So I'm going to just but there is [/INST] something I'm worried this whole thing is an interesting, I'm like who cares about comedy. There's like six comics on the planet but okay, I trust you in the, in the pilot's seat, you know what you're doing, You got you got listeners, </s><s>[INST] they've turned out long ago, [/INST] dan Carlin on here, huh? Is he around? </s><s>[INST] Yeah, we're just going back and forth on twitter. Just know it was a huge fan. He was on here before he'll be back. I've been actually really trying to volunteer myself aggressively with dan Carlin's for like a Russian episode where I can speak Russian, there's there's certain documents saying I talked with Jaco about this to certain things. I mean I just love the challenge of bringing Russian documents that I can read in Russia and they can translate and can try to capture the depth of the writing in um in the Russian language and communicate to the american audience so much is lost in translation. Like there's so much pain and poetry in the Russian language. It's just connected to the culture, every language, not every language, but many languages are uniquely able to capture the culture of the people. I mean in some way that the representation of the culture of the people and so Russian is definitely that like represents the full history and culture of the 20th century with all the atrocities, all the, all the broken promises, all those kinds of [/INST] things, norm says Russian literature is it's the most tapped into human existence than anything else. Uh norm, Macdonald big big Russian literature, Guy dostoyevsky, all that ship. </s><s>[INST] It's funny that there is a gap of comedians to there's a culture of Russian comedy like stand up comedians that are totally, yeah, I don't [/INST] know these Russians, </s><s>[INST] I mean I don't know today and I mean more from the 80s and 90s and so there was a cough. [/INST] No, I know </s><s>[INST] that's not. So there's like of course that's that's [/INST] I've never seen that offended. No, </s><s>[INST] no it's not and there's a different uh there's there's a there's like the kindest sins and the there's the edgy. [/INST] Is that Russian? What do you mean? What I thought you said there was Russian comics. </s><s>[INST] Yeah Russian, I'm comparing them. I'm giving you I'm giving you like a style of darkness uh like that's the kind of people that kind of challenge. Uh They give again this is to how important comedians are is they give a voice to people where in the soviet union you really can't like express your opposition to the government. And so comedians are exceptionally important there for just just I don't know channeling the anger even once sometimes it's not the actual opposition to the government. They're just channeling the anger, the frustration with the absurdity of life. Like you know when there's a shortage of food shortage of jobs, the the the absurdity of the bureaucracy, like the top heavy government, just all of that can only sometimes be expressed with like dark absurd humor and that actually why there's a culture of that kind of humor. You know, you gather on the table with vodka and all you can do is just talk shit and just [/INST] be offensive say horrible shit ball bust. I mean school I make school shooting jokes and people go how do you do that? I'm like well maybe that's how I deal with it. You know Like how come I gotta I gotta empathize the way you do. They were different. </s>
<s>[INST] what is existence, what his presence and what does proceeds mean? [/INST] Yeah, exactly what his existence, what is essence and what is proceeds and in fact proceeds, It starts way of talking about it and other people will talk about it differently. But here's a way of here's the way start thinks about it. This is not, I think the most interesting way to think about it, but to get you started, Sartre says there is nothing true about what it is to be you until you start existing and still you until you start living and for start, the core feature of what it is to be existing. The way we do is to be making decisions to be making choices in your life, to be uh sort of taking a stand on what it is to be you by deciding to do this or that. And the key feature of how to do that right for start is to do it in the full recognition of the fact that when you make that choice, nobody is responsible for it other than you. So you don't make the choice because God tells you to you don't make the choice because some utilitarian calculus about what what it's right to do, tells you to do. You don't make the choice because some other philosophical theory tells you to do it. There's literally nothing on the basis of which you make the choice other than the fact that in that moment you are you are the one making it. You </s><s>[INST] are conscious thinking, being that made a decision. So all the questions about physics and free will are out the window. [/INST] Yeah, that's right. If you were a determinist about the mind, if you were a physical list about the mind, if you thought there was nothing to your choices other than the activity of the brain, um that's governed by physical laws, then there's some sense in which it would seem at any rate like um you're not the ground of that choice. The ground of that choice was the physical universe and the laws that govern it. And then you have no responsibility. And so starts view is that the thing that's special about us used to be special about God, is that we're responsible for becoming the being that makes the choices that we do. And start thinks that that simultaneously empowering. I mean, it practically puts us in the place of God, and also terrifying because what responsibility? How can you possibly take on that responsibility? And he thinks it's worse than that? He thinks that it's always happening. Everything that you do uh is the result of some choice that you've made. The posture that you sit in the way you hold someone's gaze when you're having a conversation with them. Or not the choice to make a note when someone says something or not make a note, everything that you do presents you as a being who makes decisions and you're responsible for all of them. So, it's constantly happening. And furthermore, there's no fact about you independent of the choices and actions you performed. So you don't get to say it's hard for example. I really am a great writer. Just haven't written my great book yet. If you haven't written a great book, you're not a great writer. And so it's it's terrifying. It puts a huge burden on us. And um and that's why I start says on his view of existentialism human beings are the beings that are condemned to be free. Our freedom consists in our ability and our responsibility to to make these choices and to become someone through making them, and we can't get we can't get </s><s>[INST] away from that. But to him is terrifying. Not liberating in the positive meaning of the word liberating. [/INST] Well, so he he thinks it should be liberating, but he thinks that it takes a very courageous individual to be liberated by it. Um, niche, I think thought something similar. I thinks artist really coming out of an itchy and sort of tradition, but what's liberating about it? If it is it's also terrifying because it means in a certain way, you're the ground of your own being, you become </s><s>[INST] what you [/INST] do through through existing. That's one form of existentialism. That's a stark atheistic version of it. There's lots of other versions, but it's somehow um organized around the idea that it's through living your life, that you become who you are. It's not facts that are sort of true about you, independent of your living your life? </s><s>[INST] But then there is no God in that view, Does any of the decisions matter? So, how does existentialism differ from Nihilism? [/INST] Good. Okay, great question. There's two different ways that you're you're asking it. Um let me leave Nihilism to the side for just a second and think about mattering or is there any way that you can criticize someone for me for doing for living the way they do if you're an existential including yourself, including yourself. Yeah. Start addresses that, and he says, um yes, he says, there is a criticism that you can make of yourself or of others, and it's the criticism of living in such a way as to fail to take responsibility for your choices. He gives these two sort of amazing examples. One doesn't I don't know if it reads as well as for us, as it uh as it did in sort of mid-20th century Paris, but it's about a waiter. He gives this in in his big book being and nothingness, and he says, um so waiters play played still do, I think in a certain way, in paris a big role in Parisian society to be a waiter involved having a certain kind of identity, being a certain way, uh taking control of, in charge of the experience of the people that you're you're waiting on, but also, you know, really being the authority, Like, knowing that this is the way it's supposed to go. And so start imagines a waiter who does everything that a waiter is supposed to do, the perfect form of the waiter, except that you can somehow see in the way he's doing it, that he's doing it because he believes that's the way a waiter should act. Not. So, there's some sense in which he's passing off the responsibility for his actions onto some idea of what those actions should be. He's not taking responsibility for it. He's sort of playing a role and the contours of the role are predetermined by someone other than him. So he starts as acting in bad faith and thats criticize herbal because it's acting in such a way as to fail to take responsibility for the kind of being start thinks you are. So you're not taking responses. So that's one example and I think, you know, are there any teenager, if you've ever met a teenager, you've known someone who who does that teenagers try on roles? They think if I dressed like this, I would be cool. So I'll dress like this or if I spoke like this or acted like this and it's natural for a teenager who's trying to figure out what their, you know what their identity is to go through a phase like that. But if you continue to do that, then you're, you're really passing. So that's one example. The other example he gives is an example, uh not of passing off responsibility by um pretending that someone else is the ground of your choice, but passing off responsibility by pretending that you might be able to get away with not making a choice at all. So he says you're always everything you do as a result of your choices. And so he gives this other example, there you are on the first date, first date and the date, the evening reaches moments when Might be appropriate for one person to hold the hand of the other. That's the moment in the date where you are. And so you make a choice, you decide. I think it's I think it's that time and you hold the hand and what should happen is that the other person also makes a choice on starts view either they reject the hand, not that time, and I'm taking responsibility for that or they grasp the hands back. That's a choice. But there's a thing that sometimes happens which is that the other person leaves the hand their cold dead and clammy neither rejecting it nor embracing it. And start says that's also bad faith. That's also acting as if we're kind of being that we're not because it pretends that it's possible not to make a choice and where the beings who are always making choices that was a choice and you're pretending as if it's the kind of thing that you don't have to take responsibility for. </s>
<s>[INST] Well, first of all, it's not certain that that's true, it's it's possible, possible, like Sean carroll, you know, uh especially with quantum mechanics based on certain interpretation of quantum mechanics, that's that's very possible. But the question is, can you access those universe is [/INST] the </s><s>[INST] more, the more sort of specific practical question is this local pocket of the universe, our galaxy or neighboring Galaxies. Are there aliens there? What did they look like? Are they? So you can have this panspermia idea where a much larger, like uh, like daddy civilization, uh, like uh rolled by and just planted a few aliens at a similar time. Yes, a different, you know, throughout the galaxy. And those are the ones who might be interacting with their all kind of dumb as we are relatively, you know, maybe a few million years apart. And then those are the ones who are interacting with and then we have a chance to actually connect with them and communicate with them. Or it could be like much more wide open and you have these gigantic alien civilizations that are expanding very, very quickly. And the interesting thing is when you look up at the sky and you see the stars that's light from those stars, we might not be seeing the alien civilizations until they're already here, meaning like you start expanding once you get really good at expanding, you're going to be expanding very close to the speed of light. So right now we don't see much in in the sky, but there could be 11 day we wake up and it's just like everywhere and they're here? [/INST] Right? Because the amount of time the light takes to reach us? Yeah. And then the thing that I've been really fascinated by is these alternative forms of transportation that they're discussing, like the ability to harness wormholes and the, the ability to, to do things that were uh a Type three civilization is capable of. I had Mikio Kaku on my podcast recently. Fantastic. I love that guy. He's so, he's so good at taking extremely complex concepts and boiling them down for digestion and, and you know, and saying them in a way that other people can appreciate </s><s>[INST] and not being hesitant about saying wild, crazy ship that's out there, but grounded in what's actually possible. [/INST] Yeah, he's all in on this Ufo phenomenon now he's now he's like now the burden of proof is to people for people to come up with some sort of a conventional explanation for these things. He goes, because these things are defying all the concepts of physics that that we're, we currently know in terms of what our capabilities are and and propulsion systems and and so many other things that, you know, what we know about, what current science is capable of reproducing as far as what we know the problem is like these um military projects that are top secret, like how much money do they have? They have a lot of money like, but is it possible and maybe you could speak to this, Is it possible that there could be some propulsion systems that have been developed and implemented that are far beyond just a simple burning of rocket fuel, pushing the fire out the back, which forces the rocket at extreme speeds forward. That's something that does harness gravity. Something that can distort space and time and can make travel from one point to another. Uh, like preposterously fast. </s><s>[INST] Well not only is it possible, I think it's likely that that kind of stuff would be kept a secret. It's just everything you see about these um, about the way either if it's contractors like Lockheed martin or if it's due to the, the, the, the, the actual Department of Defense, they operate in complete secrecy. Just even looking at the, the history of the stealth fighter, just even stealth technology was kept a secret for a very, very long time and not until you're ready to use it and need to use it, does it become public and not officially public? It's just is being detected out in the wild. So there's going to be a process where you're secretly testing it and that might creep up, which is maybe what we're seeing and then it's waiting for the next big war, the next big reason to use the [/INST] thing. </s><s>[INST] And and so yeah, there's there's definitely technologies now, there might not be propulsion technologies that could be a i surveillance technologies that could be different kinds of stealth drones. There could be, it could be also in cyberspace, like cyber war weapons, all that kind of stuff that they're obviously going to become a secret. [/INST] I'm I'm very skeptical lately and the reason why I'm skeptical is the government keeps talking about it, The Pentagon keeps talking about it. Nasa keeps talking about it. I'm skeptical that it's their aliens. I think most likely it's a smokescreen and most likely these are some sort of like incredibly advanced drones that they've developed that they want to pretend don't exist. That seems the more likely scenario because otherwise my take is like what's the benefit of them discussing these things? Like what's the benefit of them discussing these things openly. These are, you know what the way they described it off world crafts not made from this earth. Like why why would they, why would they tell us that? I mean, unless there's an imminent danger of us being invaded and they want to prepare people so they don't freak out as much, you know, like maybe freak them out a little bit say that publicly. The new york Times article, the Pentagon discussing it all these different things. Yeah, well let let people know that this is a thing or my take is like that. I don't think they do that. I don't think they tell us. I think they, I think, I think the government has a lot of contempt for for the citizens. I really do. I think they have contempt for our intelligence. They have contempt for our need to know things. And I also think they think that they are running us. It's not we're all in this together and the government works for the people and the government is of the people. I don't think they think that way. </s>
<s>[INST] So, so when faced with a tough decision in need of advice, it's been said that the best thing one can do is to find the best person in the world who can give that advice and find a way to be in a room with them one on one and ask. So here we are. And let me ask in a long winded way I wrote this down In 1998. There are many good search engines, Lycos, excite altavista infoseek ask jeeves maybe uh yeah, who even so google stepped in and disrupted everything. They disrupted the nature of search. The nature of our access to information, the way we discover new knowledge. So now it's 2018 actually, 20 years later, there are many good personal ai assistance including of course the best from google. So you've spoken in in medical and education the impact of such an Ai assistant could bring. So we arrive at this question so it's a personal one for me but I hope my situation represents that of many other as we said dreamers and the crazy engineers. So my whole life I have dreamed of creating such an assistant. Every step I've taken has been towards that goal. Now I'm a research scientist in human centered AI here at M. I. T. So the next step for me as I sit here facing my passion Is to do what Larry and Sergey did in 98 this simple startup. And so here's my simple question. Given the low odds of success the timing and luck required the countless other factors that can be controlled or predicted. Which is all the things that Larry and Sergey faced. Is there some calculations some strategy to follow in the step or do you simply follow the passengers because there's no other choice. [/INST] I think the people who are in universities are always trying to study the extraordinary chaotic nature of innovation and entrepreneurship. My answer is that they didn't have that conversation. They just did it. They sensed a moment when in the case of google there was all of this data that needed to be organized and they had a better algorithm. They had invented a better way. So today with human centered ai which is your area of research, there must be new approaches, it's such a big field, there must be new approaches different from what we and others are doing, There must be startups to fund, there must be research projects to try, there must be graduate students to work on new approaches. Um here at MIT, there are people who are looking at learning from the standpoint of looking at child learning, right? How do Children learn starting at 81? And the work is fantastic. Those approaches are different from the approach that most people are taking. Perhaps that's a bet that you should make or perhaps there's another one. But at the end of the day the successful entrepreneurs are not as crazy as they sound, they see an opportunity based on what's happened. Let's use Uber as an example as Travis tells the story, he and his co founder was sitting in paris and they had this idea because they couldn't get a cab and they said we have smartphones and the rest is history. So what's the equivalent of that Travis Eiffel Tower, where is a cab moment that you could as an entrepreneur take advantage of whether it's in human centered Ai or something else. That's the next great startup </s><s>[INST] and the psychology of that moment. So when Sergey and larry talk about uh listen to a few interviews, it's very nonchalant, Well here's here's the very fascinating web data and uh here's an algorithm we have for, you know, we just kind of want to play around with that data and it seems like that's a really nice way to organize this data. [/INST] Well, I could say, I should say what happened remember is that they were graduate students at Stanford and they thought there's this interesting. So they built a search engine and they kept it in their room and they had to get power from the room next door because they were using too much power in the room. So they ran an extension cord over </s><s>[INST] right. [/INST] And then they went and they found a house and they had Google World headquarters of five people right to start the company and they raised $100,000 from Andy Bechtolsheim who was the son founder to do this and Dave Harriton and a few others. The point is their beginnings were very simple, but they were based on a powerful insight that is a replicable model for any startup. It has to be a powerful insight. The beginnings are simple and there has to be an innovation in in Larry and Sergei's case. It was Page Rank, which was a brilliant idea, one of the most cited papers in in the world today. What's the next one? </s><s>[INST] So you're one of if I may say richest people in the world. And yet it seems that money is simply a side effect of your passions and not an inherent goal, but it's a, your fascinating person to ask so much of our society at the individual level and at the company level and nations is driven by the desire for wealth. What do you think about this drive and what have you learned about if I may romanticize the notion the meaning of life having achieved success on so many dimensions? [/INST] There've been many studies of human happiness and above some threshold, which is typically relatively low for this conversation. There's no difference in happiness about money. It's the happiness is correlated with meaning and purpose, a sense of family, a sense of impact. So if you organize your life, assuming you have enough to get around and having a nice home and so forth, you'll be far happier if you figure out what you care about and work on that, it's often being in service to others. It's a great deal of evidence that people are happiest when they're serving others and not themselves. This goes directly against the sort of press induced uh, excitement about powerful and wealthy leaders of one. And indeed these are consequential people. But if you are in a situation where you've been very fortunate as I have, you also have to take that as a responsibility and you have to basically work both to educate others and give them that opportunity, but also use that wealth to advance human society. In my case, I'm particularly interested in using the tools of artificial intelligence and machine learning to make society better. I've mentioned education, I mentioned uh inequality and middle class and things like this, all of which are a passion of mine. It doesn't matter what you do, it matters that you believe in it, that it's important to you and that your life will be far more satisfying if you spend your life doing that. </s>
<s>[INST] Uh ego is beautiful, okay. But back to uh new, there's a bunch of things I want to ask but sort of, let's say since we're on the cabinets and the topic of drama, let me ask another drama question. Why was Newton a complicated man? Yeah, we're breaking news today. [/INST] This is like uh right was complicated. His brain structure was different. I don't know why he had a complicated young life as we've said. Um He had always been very Self contained and solitary. He had acquaintances and friends and when he moved to London, eventually he had quite a career, a career, for instance, that led him when he was famous by then the 1690s, he moves to London. He becomes first um warden of the mint. The mint is what produces coins. And coinage was a complicated thing because there was counterfeiting going on and he becomes master of the mint to the extent. Uh And a guy at MIT wrote a book about this a little bit. We wrote something on it too. I forget his name was Levin um that Newton sent investigators out to catch these guys and sent at least one of them, a famous one named Challenger to the gallows. Mhm. So he was he and one of the reasons he probably was so particularly angry at Challenger was Challenger had apparently said some nasty things about Newton in front of Parliament at some point. Fair enough. It was apparently not a good idea. </s><s>[INST] Well, he had a bit of a 10 person. You've had a bit of it clearly, [/INST] clearly. Um But he um he, even as a young man at Cambridge though, he doesn't come from wealth. He attracts um people who recognise his smarts. Uh There's a young fellow named Humphrey. Newton shared his rooms. You know, these students always shared rooms with one another became his kind of Emanu insists to uh write down what Newton was doing and so on. Uh And there were others over time who he befriended in various ways and so on. He was solitary. Ah he had, as far as we know, no relationships with either women or men in anything other than a formal way. Uh The only those get in the way relationships. Right. Well, I mean, he was he he was I don't know if he was close to his mother. I mean, she passed away, everything left him. He went to be with her after she died. He was close to his niece, Catherine Barton, who basically came to run his household uh when he moved to London and so on. And she married a man named conduit who became one of the people who controlled Newton's legacy later on and so on. So he and and and you can even see the house that the townhouse the Newton lived in in those days still there. So, </s><s>[INST] there's the story of Newton coming up with quite a few ideas during a pandemic. We're on the outskirts of a pandemic ourselves and a lot of people use that example as motivation for everybody while they're in lockdown to get stuff done. Uh So, what's that about? Can you tell the story of that? [/INST] Well, I can let me first say that. Of course, we've been teaching over Zoom </s><s>[INST] lately. And there's no zoom back then. [/INST] There was no zoom back then, although it wouldn't have made much difference because the story was Newton was so complicated in his lectures that at one point, the Humphrey Newton actually said that he might as well have just been lecturing to the walls because nobody was there to listen to it. So what difference? But </s><s>[INST] also not a great teacher. Huh? [/INST] Uh If you look at his optical notes, if that's what he's reading from </s><s>[INST] boy? Okay. [/INST] Uh No. </s><s>[INST] So what what can you say about that whole journey through the pandemic that the resulting in so much innovation short amount of time? [/INST] Well I mean there's two times that he goes home. Would he have been able to do it and do do it if he'd stayed in Cambridge? I think he would have. I don't think it really. Although I do like to tell my advanced students when I lecture on the history of physics to the physics and chemistry students especially we've been doing it over zoom in the last year when we get to Newton and so on. Because these kids are 21, I like to say well you know when Newton was your age and he had to go home during an epidemic, Do you know what he produced? </s><s>[INST] So can you actually summarizes for people who don't know how old was Newton? And what did he produce? [/INST] Well Newton goes up to Cambridge as it said when he's 18 years old and 16, 60 And the so called Miraculous year. The Annus Mirabilis where you get the development in the calculus and an optical discoveries especially is 1666. Right So he's what 24 years old at the time. But judging from his the notebooks that I mentioned he's already before that come to an awful lot of developments over the previous couple of years. Uh doesn't have much to do with the fact that he twice went home. It is true that the optical experiments that we talked of a while ago with the light on the wall moving up and down. We're done at home. In fact you can visit the very room he did it in to this day. Yeah it's very cool. And if you look through the window in that room there is an apple tree out there in the garden. </s><s>[INST] So you might be wrong about this. Uh I thought you were lying to me. What? Maybe there's an apple involved after all [/INST] It's not the same Apple tree but it's cutting how do you know it's just they don't they don't last that long but it's 400 years ago. Not I </s>
<s>[INST] It takes a brave person, a person of character to not buy in and I'm I'm like a like a baby deer trying to find his legs, you don't have to buy in because I love people and I think I'm kind of an idiot. And so when other people say do this and do that, it uh there's a, there's a pressure there. It's actually very difficult to not listen necessarily to the advice of others and yet keep yourself fragile and open to the world, it's easy to be like, I'm always right, you know, just kind of sticking a ground, but if you want to be like vulnerable, if you want to connect with people and just wear your heart on your sleeve, then you're going to listen to them? I mean that's the double edged sword of it and but then again, that pain, like if you don't let it destroy, you can grow grow from that has fame affected you at all. Did you unplug from the system at some point? [/INST] Same, I've always been sort of removed, I don't feel like I'm part of any system. </s><s>[INST] Do you feel famous? Um [/INST] I'm aware that when I go out, people, you know, say nice things to me, which is great, </s><s>[INST] but [/INST] that's about it, that's about as far as it, </s><s>[INST] but it doesn't affect your art, about your creativity or your thoughts, like when you're sitting alone and thinking about the world, [/INST] it can't it's a destructive force. The the thing, the reason that you're who you are and the reason that you're finding the success you're finding is because you've been true to yourself, to get to that stage. So to start changing that to either conform to someone else's idea of what you should be doing, It just seems like it doesn't make sense. </s><s>[INST] Do you have a sense of who you are? Because I don't necessarily have a [/INST] I don't know, I I know that I really like making good things and I know that I'm crazy about it in that it's like an obsession and I want things to be as good as they could be, whatever it is, and if I'm if I finish a music project and I have a window of time where I'm not working on music, I might be moving the furniture around in the house. You know, I'm always looking for a product, a creative outlet to find a way to make something better. Or there was a period of time where I was in a weird corporate situation that was, that didn't allow me to flourish and I turned, I focused the creativity and on myself and I lost a bunch of weight and changed my life. And so </s><s>[INST] that was the kind of art, like you've gone through the whole process of losing weight, getting in shape, being healthy. That was a kind of creative act. [/INST] It certainly was, it wasn't an intentional creative act, but I had a lot of energy and I just, a series of events happened. I read a book at the time, that was my heaviest. I weighed about £318 and I've never been, I've been sedentary in my whole life, basically laying on a couch, working on music. So I've never been physically active in my life And read a book about a guy named Stu Mittleman, a runner who ran 1000 miles in 11 days. And I thought, Wow, I, you know, get out of breath walking to the corner and another human being can run 1000 miles in 11 days. I feel like I have bad information, you know, I'm doing clearly I'm doing something wrong and, and I reached out to a person that you mentioned in the book, film, Atherton </s><s>[INST] who was a legend, I really appreciate him as well. He's math 1 80 method to, he's such an interesting, I think he focuses on [/INST] heart rate training and he was the first person to talk about essentially paleo keto diet for </s><s>[INST] 40 [/INST] years ago </s><s>[INST] for a person who is going to be healthy, who can exercise and actually perform at an early level. He's the first person when I um, you know, talking about heart rate training him and other endurance athletes, he influenced, he gave me permission to like run [/INST] slower. </s><s>[INST] This is the first time I realized, oh, I can run long distances if I just run slower and and I take that seriously. And I actually fell in love with running very much so because for me, everyone's different. But for me, the love of running happens in the longer distances. [/INST] Did you read Born to run? Great book, </s><s>[INST] Amazing book. There is something special about running and everybody has their own, their own journey with it and even ultra marathon running, those kinds of things. It's, it's a, it is like many journeys, one that can pull you in, like you won't be the same person after. And I, I try to be delivered about making deliberate about making choices after which you will not be the same [/INST] person. </s>
<s>[INST] their existence is only meaningful in how it relates to me. But it's still meaningful. It just seems like a very difficult leap to take that I don't care that a million people die. That seems to be, even with envy, there seems to be a big feeling and thought to have if you at all care about them. Are other people, I guess, tools [/INST] for alleviation of your sense of inadequacy? Right, I mean, I don't even care about in that being caring at all. I mean, caring about in that noticing that the person exists, right? I mean, someone who wants money and notices that there's a $100 bill out cares about that. They don't care about the $100 bill and that doesn't mean anything to them. It's of thoughts and feelings, but it's gonna attract attention. They care about it because it's something that they want, right, the same way people will care about others, but only from the perspective of, do you have things that I want? Or can I feel better about myself by taking something from you, </s><s>[INST] by making things worse for you? People often talk about narcissism as like the opposite of empathy, but sort of empathy, again, depends how you define it, but it's a careful consideration of the mental space of another person, of how the other person sees the world. And so you're kind of saying that narcissistic people would also be very good at that in order to understand how maybe the other person could be manipulated or something [/INST] to alleviate your sense of inadequacy. Right, so there's a difference between the mechanics of empathy. So let's say, and we can define things different ways, let's say empathic attunement is the ability to be attuned and to think, okay, what's going on in you? What might you be thinking? What might you be feeling? Now some people have a lot of empathic attunement, but we could look at that as mechanistic, right? It doesn't equate to care, right? And empathic attunement can come along with empathy or not. Right, so yes, people who are narcissistic, they can mentalize well. So you mentalize meaning the ability to understand or to consider thoughts, feelings, motivations and other people, right? So people who are narcissistic can have empathic attunement or mentalization depending upon how we wanna describe those things, but that has nothing to do with care, </s><s>[INST] with actual empathy or kindness or consideration. So in that sense, empathy usually popularly really used means that you care, like your happiness is aligned. There's this, I need to read this book. I've read so little science fiction. There's been one of my goals for this year to catch up on some science fiction. So Robert Highland from Stranger in a Strange Land has this quote about love, which is, love is that condition where another person's happiness is essential to your own. So that's a good definition, I guess, of empathy where you're very sensitive, so mechanistically very sensitive to the state of another person's mind and your goal is to maximize their happiness. It's like essential to your own happiness. So the happinesses are aligned and when that's like elevated to its highest forms, you can call that love or romantic love and friendship and so on. [/INST] Okay. There's one more thing about the narcissist is some people can be sort of benign narcissists where they want great things for themselves, right? But if they have enough great things, they can sort of tolerate others being happy too. And these are people who sometimes are actually quite highly liked, right? Because they have to have the most money, the most power, the most of anything, anything more than anyone else could challenge. But as long as I have that, it's okay that you have some too, right? And then that can make you happy and can make you like me, right? So benign narcissists can be well-liked from that perspective, but it's still all about them and that can change if, for example, there's a scarcity of resources now, right? But they're generally, they're not people who are being overtly destructive. Although that they're over the border into the envy territory, right? Melignant narcissists are very different where they then want to have everything. So, even if I have a thousand times more than you, do I still envy you what you have because I don't think I can feel good enough about myself unless I have everything. And once I have everything I won't feel good enough about myself either and then I'll have to have more, right? It's like, that's malignant narcissism, which we think of as sociopathy, and we can define these words in different ways, but they're very, very negative concepts. That's profound sociopathy, malignant narcissism, </s><s>[INST] envy width-large. So sociopathy is malignant narcissism. [/INST] That's a convenient way to think about it, as malignant narcissism. No, because we can do sort of sociopathic things but not be sociopathic like, well, you can tell a white lie. It's like sort of sociopathy on steroids, right? Is then, you know, envy writ large is malignant narcissism. </s><s>[INST] Well, just like you're saying, like there's empathic attunement, as you said. So there's the mechanistic aspect of empathy and sociopathy. And then there's the big label you get attached if you're just doing that thing regularly, I guess. Living your life through that lens, right? Yeah. And is there a nice spectrum that's like narcissism, sociopathy and psychopathy? Is it all the same kind of nice stroll [/INST] through the woods, off the cliff? Living your life through that lens, right? Not really because the words don't have clear definitions like psychopathy and sociopathy. There's no real definition of psychopath or psychopathy. Does that mean someone's sociopathic but psychotic? Like there's really not, we end up using those words colloquially, right? Which is why, you know, concepts that we can define like envy, empathic attunement, narcissism, even though there might be nuances and definitions, like we can define them in ways that are widely accepted, </s>
<s>[INST] Okay, wait a minute. Did you just say that you think in terms of likelihood life started [/INST] on Mars, statistically speaking, life started on Mars and seeded Earth? It could be possible because Mars was habitable for the type of life that we have right now, type of chemistry before Earth. It seems to me that Mars got searching doing chemistry. It started way before. Yeah, and so they had a few more replicators and some other stuff. And if those replicators got ejected from Mars and landed on Earth, an Earth would be like, I don't need to start again. Thanks for that. And then it just carries on. I think we will find evidence of life on Mars, either life we put there by mistake, contamination, or actually the earliest remnants of life. And that would be really exciting. It's a really good reason to go there. But I think it's more unlikely because of the gravitational situation in the solar system if we find life in the outer solar system. </s><s>[INST] It started way before, right? Titan and all that. That would be its own thing. Exactly. Wow, that'd be so cool. If we go to Mars and we find life that looks hella-lot similar to Earth life, and then we go to Titan and all those weird moons with the ices and the volcanoes and all that kind of stuff, and then we find there something that looks, I [/INST] know, way weirder. Yeah. Some other, some non-RNA type of situation. But we might find almost life like in the prebiotic chemical space. And I think there are four types of exoplanets we can go look for, right? Because when JWST goes up and touch wood, it goes up and everything's fine. When we look at a star, well, we know statistically most stars have planets around them. What type of planet are they? Are they going to be dead? Are they going to be just a prebiotic origin of life coming? So are they going to be technological? And, you know, so we have intelligence on them and will they have died? So, you know, from, you know, had life on them. Those are the four states. And so, and suddenly it's a bit like I want to classify planets the way we classify stars. Yeah. And I think that in terms of rather than having this, oh, we've found methane, there's evidence of life. We've found oxygen, that's the evidence of life. We've found whatever molecule marker and start to then frame things a little bit more. </s><s>[INST] Those are the four states of states, which by the way, you're just saying four, but there could be, [/INST] before the dead, there could be other states that we humans can't even conceive of. Just prebiotic, almost alive, you know, got the possibility to come alive. </s><s>[INST] I think there could be a post-technological, like whatever we think of as technology, there could be a like pre-conscious, like where we all meld into one super intelligent conscious [/INST] or some weird thing that naturally happens over time. Yeah. I mean, I think that all </s><s>[INST] better than the metaverse. Yeah, we are. We join into a virtual metaverse and start creating, which is kind of an interesting idea, almost arbitrary number of copies of each other, much more quickly to can mess with different ideas in mind. Like I can create a thousand copies of Lex, like every possible version of Lex, and then just see like, and then I just have them like argue with each other and like until like in the space of ideas and see who wins out. How could that possibly go wrong? But anyway, but there's, especially in this digital space where you could start exploring with AIs mixed in, you could start engineering arbitrary intelligences. You can start playing in the space of ideas, which might move us into a world that looks very different than a biological world. Like our current world, the technology is still very much tied to our biology. It's, we might move past that completely. Oh, definitely. We definitely will. We definitely, because that could be another phase then. Sure. Because then [/INST] you, but we definitely will. But I did say technological. So I think I agree with you. I think so. You can have, let's get this right. So dead world, no prospect of life. Prebiotic world, life emerging, living and technological, and you probably, and the dead one, you probably won't be able to tell between the dead never been alive and the dead one. Maybe you got some artifacts and maybe there's five, there's probably not more than five. And I think the technological one could allow, could have life on it still, but it might just exceeded because, you know, one way that life might survive on earth is if we can work out how to deal with the coming, the real climate change that comes when the sun expands. There might be a way to survive that, you know? But yeah, I think that we need to start thinking </s><s>[INST] statistically when it comes to looking for life in the universe. Let me ask you then, sort of statistically, how many alien civilizations are out there in those four phases that you're talking about? When you look up the stars and you're slipping on some wine and talking to other people with British accents about something intelligent and intellectual, I'm sure. [/INST] Do you think there's a lot of alien civilizations looking back at us and wondering the same? My romantic view of the universe is really taking loans from my logical self. So what I'm saying is I have no doubt, I have no idea. But having said that, there is no reason to suppose that life is as hard as we first thought it was. And so if we just take earth as a marker, and if I think that life is a much more general phenomena than just our biology, then I think the universe is full of life. And the reason for the Fermi paradox is not that they're not out there, it's just that we can't interact with the other lifeforms because they're so different. And I'm not saying that they're necessarily like hasn't depicted in Arrival or other, you know, I'm just saying that perhaps there are very few universal facts in the universe. And that and maybe that is not, it's quite hard, our technologies are quite divergent. And so I think that it's very hard </s>
<s>[INST] How much is fast they I of course is free. [/INST] Everything we do is free. We have no revenue sources of any kind, it's just a service to the community </s><s>[INST] years ST okay. Once a person understands the basics, trains a bunch of models. If we look at the scale of years, what advice do you have for someone wanting to eventually become an expert? [/INST] Train lots of models, specifically trained lots of bottles in your domain area. So an expert what? Right. We don't need more expert. Like uh, create slightly evolutionary research in areas that everybody's studying. We need experts at using deep learning to diagnose </s><s>[INST] malaria. [/INST] Or we need experts at using deep learning to analyze language to study media bias or we need experts in, um, um, analyzing fisheries to identify problem areas in the ocean. You know, that that's, that's what we need. So like become the expert in your passion area and this is a tour which you can use just about anything and you'll be able to do that thing better than other people, particularly by combining it with your passion and domain expertise. </s><s>[INST] So that's really interesting. Even if you do want to innovate on transfer learning or active learning, your thought is it means one I certainly share is you also need to find a domain or dataset that you actually really care [/INST] for. If you're not working on a real problem that you understand? How do you know, if you're doing it any good, how do you know, if your results are good, how do you know, if you're getting bad results, why you're getting bad results? Is it a problem with the data? Like how do you know, you're doing anything useful? Yeah. The only to me the only really interesting research is not the only, but the vast majority of interesting research is like try and solve an actual problem and solve it really well. </s><s>[INST] So both understanding sufficient tools on the deep learning side and becoming a domain expert in particular domain, really things within reach before anybody. [/INST] Yeah, I mean to me, I would compare it to like studying self driving cars, having never looked at the car or been in a car or turn the car on, which is like the way it is for a lot of people, they'll study some academic data set where they literally have no idea about that by </s><s>[INST] the way, I'm not sure how familiar with autonomous vehicles, but that is literally you describe a large percentage of robotics folks working self driving cars as they actually haven't consider driving. They haven't actually looked that we're driving, looks like they haven't driven it [/INST] a problem because you know, when you've actually driven, you know, like these are the things that happened to me when I was driving </s><s>[INST] it, there's nothing that beats the real world examples of just experiencing them. You've created many successful startups, what does it take to create a successful startup? [/INST] Same thing is becoming successful, deep learning practitioner, which is not getting up so you can run out of money or run out of time or run out of something, you know, but if you keep costs super low and try and save up some money beforehand. So you can afford to have some time then just sticking with it is one important thing. Doing something you understand and care about is important by something. I don't mean the biggest problem I see with declining people is they do a PhD in deep learning and then they try and commercialize their PhD is a waste of time because that doesn't solve an actual problem. You picked your PhD topic because it was an interesting kind of engineering or math or research exercise. But if you've actually spent time as a recruiter and you know that most of your time was spent sifting through resumes and you know that most of the time you're just looking for certain kinds of things and you can try doing that with a model for a few minutes and see whether it's something which the model is going to do as well as you could, then you're on the right track to creating a start up and then I think just being just be pragmatic and try and stay away from venture capital money as long as possible, preferably forever. </s><s>[INST] So yeah, at that point, do you venture capital. So did you were able to successfully Iran startups with self funded? [/INST] So my first two was self funded and that was the right way to do it. </s><s>[INST] That's scary. [/INST] No species startups are much more scary because you have these people on your back who do this all the time and you have done it for years telling you grow, grow, grow, grow and I don't, I don't care if you fail. They only care if you don't grow fast enough. So that's scary. Where else doing the ones myself well with partners who were friends. It's nice because like we just went along at a pace that made sense and were able to build it to something which was big enough that we never had to work again. But it was not big enough that any VC would, I think it was impressive and that was enough for us to be excited, you know. Uh, so I thought that so much better way to do things that most people </s><s>[INST] generally speaking that for yourself. But how do you make money during that process? Do you cut into savings? So [/INST] Yeah. So for, so I started fast male and optimal decisions at the same time in 1999 With two different friends and for fast mail I guess I spent $70 a month on the server. And when the server ran out of space, I put a payments button on the front page and said if you want more than 10 mega space you have to pay $10 a yeah. </s>
<s>[INST] insight in the ordinary financial markets. And the market would, if it's efficient, would be able to become better and better predicting the powerful ideas that the [/INST] individual is able to generate. The variance around the mass of the electron neutrino would decrease with time as we learned that value of that parameter better and any other parameters </s><s>[INST] that we wanted to estimate. You don't think those markets would also respond to recency of prestige [/INST] and all those kinds of things? They would respond, but the question is, if they might respond incorrectly, but if you think they're doing it incorrectly, you have a profit opportunity where you can go fix it. So we'd be inviting everybody to ask whether they can find any biases or errors in the current ways in which people are estimating these things from whatever clues they have. </s><s>[INST] There'll be a correction. There's a big incentive for the correction mechanism. In academia, [/INST] currently, it's the safe choice to go with the prestige and there's no... Even if you privately </s><s>[INST] think that the prestige is overrated. Even if you think strongly that it's overrated. Still, you don't have an incentive to defy that publicly. You're going to lose a lot unless you're a contrarian that writes brilliant blogs and then you could talk about it in the podcast. [/INST] Right. Initially, this was my initial concept of having these betting markets on these key parameters. What I then realized over time was that that's more what people pretend to care about. What they really mostly care about is just who's how good. That's what most of the system is built on is trying to rate people and rank them. I designed this other alternative based on historical evaluation centuries later just about who's how good because that's what I think most of the customers really care about. Customers. I like the word customers here. Humans. Every major area of life, which has specialists who get paid to do that thing, </s><s>[INST] must have some customers from elsewhere who are paying for it. Who are the customers for the mass of the neutrino? Yes, I understand a sense people [/INST] who are willing to pay for a thing. That's an important thing to understand about anything. Who are the customers? What's the product? Medicine, education, academia, military, etc. That's part of the hidden motives analysis. Often people have a thing they say about what the product is and who the customer is and maybe you need to dig a little deeper to find out what's really going </s><s>[INST] on. A lot deeper. You've written that you seek out quote viewquakes. You're able as an intelligent black box, word generating machine. You're able to generate a lot of sexy words. I like it. I love it. Viewquakes, which are insights which dramatically changed my world view, your world view. You write, I loved science fiction as a child, studied physics and artificial intelligence for a long time each, and now study economics and political science, all fields full of such insights. So let me ask, what are some viewquakes or a beautiful surprising idea to you from each of those fields, physics, AI, economics, political science? I know it's a tough question. Something [/INST] that springs to mind about physics, for example, that just is beautiful. I mean, right from the beginning, say special relativity was a big surprise. You know, most of us have a simple concept of time and it seems perfectly adequate for everything we've ever seen. And to have it explain to you that you need to sort of have a mixture concept of time and space where you put it into the space-time construct, how it looks different from different perspectives, that was quite a shock. And that was, you know, such a shock that it makes you think, what else do I know that, you know, isn't the way it seems? Certainly quantum mechanics is certainly another enormous shock in terms of from your point, you know, you have this idea that there's a space and then there's, you know, point particles at points and maybe fields in between. And quantum mechanics is just a whole different representation. It looks nothing like what you would have thought as sort of the basic representation of the physical world. And that was quite a surprise. What would you say </s><s>[INST] is the catalyst for the viewquake in theoretical physics in the 20th century? Where does that come from? So the interesting thing about Einstein, it seems like a lot of that came from like almost thought experiments. It wasn't almost experimentally driven. And with, actually, I don't know the full story of quantum mechanics. How much of it is experiment, like where, if you look at the full trace of idea generation there, of all the weird stuff that falls out of quantum mechanics, how much of that was the experimentalist? How much was it the theoreticians? But usually in theoretical physics, the theories lead the way. So maybe can you elucidate like [/INST] what is the catalyst for these? The remarkable thing about physics and about many other areas of academic intellectual life is that it just seems way overdetermined. That is, if it hadn't been for Einstein or if it hadn't been for Heisenberg, certainly within a half a century, somebody else would have come up with essentially the same things. Is that something you believe? Yeah. Yes. So I think when you look at sort of just the history of physics and the history of other areas, some areas like that there's just this enormous convergence. The different kind of evidence that was being collected was so redundant in the sense that so many different things revealed the same things that eventually you just kind of have to accept it because it just gets obvious. Yeah, so if you look at the details, of course, you know, Einstein did it for somebody else, and it's well worth celebrating Einstein for that. And, you know, we, by celebrating the particular people who did something first or came across something first, we are encouraging all the rest to move a little faster, to try to push us all a little faster, which is great, but I still think we would have gotten roughly to the same place within half-century. So sometimes people are special because of how much longer it would have taken. So some people say general relativity would have taken longer without Einstein than other things. I mean, Heisenberg quantum mechanics, I mean, there were several different formulations of quantum mechanics all around the same few years, means no one of them made that much of a difference. We would have had pretty much the same thing regardless of which of them did it exactly when. Nevertheless, I'm happy to celebrate them all. But this is a choice I make in my research. That is, when there's an area where there's lots of people working together, you know, who are, of course, sort of scoping each other and getting getting your results just before somebody else does. You ask, how much of a difference would I make there? You know, at most I could make something happen a few months before somebody else. And so I'm less worried about them missing things, so when I'm trying to help the world like doing research, I'm looking for neglected things, I'm looking for things that </s>
<s>[INST] I think this conversation is going to continue for quite a while. Michael has a new book on the topic coming out eventually one day, so you're working also on the still called the white pill. [/INST] The white pill, yeah. And the first line of the white pill is Ayn Rand did not laugh. I'm not joking, that's literally the first line. I believe you. Because it opens up with her, who knows what the book's going to look like when it's done, but as of now, that's the beginning, because it opens up with her testimony at the House Un-American Activities Committee, where she's trying to explain to these Congress people what it was like when she left the Soviet Union, and they are just befuddled by it. Can you explain she did not laugh? Well, because the first line, the fountainhead, spoiler alert, is Howard Rourke laughed. So this is a little inversion of that, it says Ayn Rand did not laugh, because Ayn Rand was a huge fan of America, as am I. She took our political system very seriously. She had enormous reverence for institutions. One example of this is one of the villains of the Atlas Shrugged is based on Harry Truman. I think Thompson is the character's name. And because she had such respect for the title of president, she refers to him as the chairman. She couldn't even bring herself- She had a huge respect for the presidency. I wonder if she'd still have it, given the last string of presidents we've found, the last string of presidents we've found. So having her, which sets up the broader point of the book, which I'm sure I'll be back on the show to discuss assuming this bridge hasn't been burned, but I'll try my best. </s><s>[INST] All three of us are canceled. Some are more canceled than the others. [/INST] I don't know. I don't know. I'm looking at you, Michael. The point being, which sets up the broader point in the book is how ignorant many people are in the West about the horrors of Stalinism and communism, but also how many people in the West were complicit in saying to Americans, go home, everything's fine. This is great. Sure, this is why Pence and Sava race are sure there are mistakes. And they really made a point to downplay really gratuitously some of the unimaginable atrocities of the communism. And just one more sentence. And going through the work and learning about what they actually did is so jaw-dropping that if I didn't know about it, and many people I'm friends with who are historians who are interested in the space, this isn't common knowledge to them, then we can assume that almost no one knows about it. And I think it's very important for people to appreciate, whether Republican, Democrat, liberal, whatever, how much of a danger this is. And I think Americans have this, there's a book called It Can't Happen Here, I think by Sinclair Lewis about a fascism coming to America. American exceptionalism has a positive context, but also have a negative context where you think we're invincible. All these horrible things that have these other countries that can't possibly happen here where America was special, and it's completely an absurdity. I'm looking at you. Have you seen the movie, Mr. Jones? My friend wrote it. No, I haven't. But Walter Durante and his quotes, I have a thread on Twitter, Walter Durante, for those who don't know, he won a Pulitzer because he was the New York Times man in Moscow. And endlessly, he was talking about how great it was, how if you hear about this famine in Ukraine, this is just propaganda, I went to the villages, everyone's happy and fed. A lot of it was explicit lies. And when you realize you're talking about, let's give them the absolute benefit of doubt, an accidental genocide, it's still mind boggling. And also, Anne Applebaum, who's just a phenomenal writer, she wrote a book called Red Famine, Stalin's War in Ukraine. And she talks about how what people in America don't appreciate is how clever in their sadism the Soviets were. And what they knew to do in Ukraine is everyone is starving. So they knew if you got some meat on your bones, you're hiding food. So they come back at night, take your hand, put in the door jam, keep slamming the door, ransack your house. They didn't have to find the food, burn down your house, take all your clothes, goodbye and good luck. I don't recall saying good luck. So it's- So I highly recommend the movie because it's very well done. Okay. It's very well directed. It's beautifully made. It's stunningly effective. Again, illustrating exactly that. The scenes in Ukraine during the famine, I mean, it just, it's crushing. And it shifts to black and white. It's very, very well made aesthetically. So highly recommend it. And it's written by Andra Chalupa. She's a Ukrainian friend of mine. She interests me, Yanmi Park, who's a big North Korean defector. And this is the kind of thing where I think more people need to, when I wrote the New Right, which talks a lot about the Nazis or the kind of neo Nazis won their big complaints against people who are Jewish. She's like, oh, we hear all about the Holocaust, how can we talk about the holodomor? I'm like, I'm trying to do my part. I agree with you that we need to be talking about the holodomor. Absolutely. Yeah, I agree. That we need to be talking about the holodomor. Absolutely, yeah, absolutely. And it's sad. There aren't more movies that are anti-Soviet, which tells you a lot about the view of the intelligentsia. It's a great idea. It just was badly implemented. And no, it's a rotten idea. It's an evil idea. And it was implemented. Exactly. It was implemented exactly how it has to be implemented. There's no alternative. Absolutely. </s>
<s>[INST] Yeah. You know, I have a little bit of that. I, I seem to uh see the magic in a lot of moments like I have a deep, it's obviously not obviously, but it seems to be chemical in nature that I just am excited about life. I love life. I love like stupid things. It feels like I'm high a lot unlike mushrooms or something like that where you'd really appreciate that. So you're able, I'm able to detect something about the environment that maybe others don't, I don't know. But like I seem to be over the top grateful to be alive and a lot of for a lot of stupid reasons and that's in there somewhere. I mean, it's, it's kind of interesting because, um, it really is true that our brains the way we were brought up, but also the genetics enables us to see certain slices of the world. And um, some people are probably more receptive to anomalous information. They see the they see the magic, the possibility in the novel thing as opposed to kind of uh, finding the pattern of the common of the regular. Some people are more, wait a minute. This is kind of weird. I mean, a lot of those people probably become scientists to like, huh, like there's this pattern happening over and over and over and then something weird just happened. And then you get excited by that weirdness and start to pull the string and discover what is at the core of that weirdness. And perhaps is that, you know, maybe by way of question, how does the human perception system deal with anomalous information? Do you think, [/INST] well, it first tries to classify it and get it out of the way if it's not food, if it's not sex, right? If it's not uh in the way of my desires or if it is in the way of my desires, then you focus on it. And so the I think the question is how much spare processing power, how much CPU cycles do we spend on things that are not those core desires? </s><s>[INST] What uh is the most kind of um memorable, powerful ufo encounter report you've ever heard just to your person on a personal level, Like there's something that was really powerful. [/INST] Well I mentioned the Zimbabwe one that's particularly interesting and one that actually most people don't know about, but family Driving down the highway, two little girls in the back open, glass topped car. And the little girls see a craft right over their car. This is in the middle of the day, on a busy highway. The mother sees it. Nobody can they look around, Nobody else seems to see it. So the girls take out their camera, take a picture of it and then they get home. Uh They look at the picture, there's no craft. But there's a little object About 30 ft above there. Car or so, probably about three ft across, kind of star shaped. It's not the craft, but it's something else. There's obviously there was something there. And so what were they seeing? Were they seeing a projection? Were they seeing? And why we're only they seeing it. </s><s>[INST] And the photograph was capturing something very different than that we're seeing. There's still an object. What can you give a little bit of context? Is this from modern day? It's [/INST] modern day. Oh yeah, there's a camera. </s><s>[INST] I mean they had a cell phone camera and this is like a report provided by the way. Where is like a central place to provide a report? Is this [/INST] oh, there's move on. But this isn't public. I've seen the picture. </s><s>[INST] Oh, this is something you've directly interacted [/INST] with. Yeah, yeah, I've seen the </s><s>[INST] picture. So those moments like that they captivate your [/INST] uh well it's it's so different. It doesn't fall into the standard story at all. But it also, but in another way it's kind of a it's a clear renunciation of this notion that when people see events, they don't all see the same thing. Now. We've heard this about traffic accidents, different people will see the color of the car differently or the chain of events differently and just tells you that memory isn't anywhere near what we think it is. But the issue around the so called Ufo reports is that the same people will see a very different thing almost as if whatever it is is projecting a is projecting something into the mind rather than it being real, right? Rather than it being a real manifestation, you know, material in front of you. It's actually almost some sort of an altered virtual reality that is imposed on you. I mean, you know, I think the company meta and all the virtual reality companies would love to have something like that, right? Well you don't have to actually wear something on your face to experience a virtual reality? What happens if you could just project it? </s>
<s>[INST] embracing the spirit of play. So what you have this, when you're lecturing, you're going in front of the crowd, you thought of a question you get on the stage, first of all, are you nervous at all? [/INST] I'm very nervous when I'm sitting down thinking through the structure initially, which is why my wife and I have been doing Q. And A's and that's easier on </s><s>[INST] me. It's the uh it's the way comedians are nervous, like joe Rogan just did his special. So this weekend. And so he now has to sit nervously like a comedian does, which is like, I have no material now, I have to start from scratch [/INST] when I was doing the lectures constantly instead of Q and A's </s><s>[INST] basically [/INST] what I was doing was writing a whole book chapter every night. And you know, now that's a bit of an exaggeration, because I would return to themes that I had developed, but it's not really an exaggeration because I didn't ever just go over wrote material ever. So it was it's very demanding and that part's nerve wracking because I sit down, it's an hour before the show and I think can I can I do this? And you know, the answer is what you did it 1000 times, but that's not this time, It's like, can I come up with a question, can I think through the structure, can I pull off the spontaneous narrative, can I pull it together? And the answer is, I don't know. And so then I get it together in my mind, I think, and that's hard, It's it takes effort and it's nerve wracking. Okay, I got it. But then there's the moment you go out on stage and you think, well I know I had it, but can I do it no notes. And then the question is, well you're gonna find out while you do it. And so then I go out on stage and I don't talk to the audience, I talked to one person at a time and you can talk to one person, you know, because you know how to do that. So I talked to a person and not too long because I don't want to make them too nervous and then someone else and someone else and then I'm in contact with the audience. And then I can tell if the words are landing and I listen, it's like, are they wrestling around? Are they dead quiet? Because you want dead quiet? </s><s>[INST] You're so I see that's what focus sounds like you're you're in it together, then [/INST] you bet. Well, and I also here's a good rule if you're learning to speak publicly, I never say a word Until everyone is 100% quiet. And that's it's a great way to start a talk because you're setting the frame and if the frame is well, I'll talk while you're talking the messages while you can talk. This is a place where everybody can talk. It's like, no, it's not. This is a place where people pay to hear me talk so I'm not gonna talk till everyone's listening. And so then you get that stillness and then you just wait because that stillness turns into an expectation and then it comes turns into a kind of nervous expectations. Like what the hell is he doing? It's not manipulative, It's a sense of timing. It's like just when That's right, you think OK now it's time to start. Well </s><s>[INST] that's the interesting thing about that nervous expectation is from an audience perspective we're in it together. [/INST] Yeah. </s><s>[INST] I mean, there is into that silence. There's a togetherness to it. [/INST] Of course, it's the union of everyone's attention. Yeah. And that's and that's a great thing. I mean, you love that at a concert when everyone it's not silenced then, but when everyone's attention is unified and everyone's moving in unison, it's like we're all worshiping the same thing, right? Is when that would be the point of the conversation. The point of the lecture and the worship is the direction of attention towards it. And it's, you know, it's communion because everyone's doing it at the same time. And so, I mean, there's not much difference between lecture theater and a church in that regard, writes the same fundamental layout and structure and they're very integrally associated with one another. One really grew out of the other, the lecture theater grew out of the church. So it's it's perfectly reasonable to be thinking about it in those terms. And so, and then, okay, so after the lecture, we play a piece of music that is a piece of music that I've been producing with some musicians for a couple of books I'm going to release in the fall, terrible books abc of childhood tragedy, they're called dark, dark books, dark and comical books, terrible books, the heartbreaking illustrations, We set them to music. And so we play a piece from that. And then afterwards I usually meet about 150 people to have photographs. And so each of those is a little </s><s>[INST] is there a little sparkle of human connection [/INST] a lot? </s><s>[INST] A [/INST] Lot. It's, it's very intense. 10 seconds with every person you think, how can 10 seconds be intense? It's like pay enough attention, gets intense real quick. </s><s>[INST] Does it break your heart to say goodbye so many times? [/INST] It's like being at a, in a wedding line up at a wedding that you want to be at and everybody's dressed up. And that's so weird because I bought these expensive suits when I went on tour and it broke my heart because I spent so much money on them. I thought, God, that's completely unconscionable. I thought, no way </s><s>[INST] man, I'm [/INST] In this 100%. And so I'm gonna dress with respect. And Like 60% of the audience comes in two or three piece suits, they're all dressed up. Then there's this line to greet me and they're all happy to see me. That's not so hard to take. You know, although it is in a sense right? Because normal interactions are pretty shallow and you think I don't want shallow interactions like, yes, you do most of the time. It's </s>
<s>[INST] So the call to adventure, the adventure starts uh not trying to analyze the probabilities of the situation, but uh using what instinct, how do you dive in? [/INST] It? Is it is being a simultaneously being a dreamer and the realist, It's to know how to do that. Well the Pole comes from a Pole to Adventure for whatever reason, uh I can't tell you how much of it's genetics and how much is environment. But there's a early on, it's exciting, that notion is exciting. Being creative is exciting and so one feels that then one gets in the habit of doing that. Okay, how do I know, how do I learn very well and then how do I imagine? And then how do I experiment to go from that imagination? So it's that process, that one and then one more one does it, the more the better one becomes that </s><s>[INST] you mentioned shapers. Elon musk, Bill Gates, what who are the shapers that you find yourself thinking about when you're constructing these ideas, the ones that define the archetype of a shape or for you? [/INST] Well, as I say, a shaper for me is somebody who comes up with a great visualization um usually a really unique visualization and then actually builds it out and makes the world different changes the world in that kind of away. So when I look at it marc Benioff with Salesforce chris Anderson with ted Mohammad Yunus with social enterprise and philanthropy Geoffrey Canada and Harlem Children's Zone, there are all domains have shapers who have the ability to visualize and make extraordinary things happen. </s><s>[INST] What are the commonalities between some of them? [/INST] The commonalities are first of all the excitement of something new, that culture adventure and, and again that practicality, the capacity to learn the capacity then um, they're, they're able to be in many ways full range. That means they're able to go from the big, big picture down to the detail. So let's say for example, uh, Elon musk, he describes, he gets a lot of money from selling Paypal is interesting. Paypal, he said, why isn't anybody going to mars or out of space? What we're gonna do if the planet goes to hell and how do I, how are we going to get that? Nobody's paying attention to that. He doesn't know much about it. He then reads and learns and so on says, I'm going to take, okay, half of my money and I'm gonna put it in there and I'm going to do this thing and he learns about and he's got creative, okay, that's one dimension. And so he gave me the uh, keys to his car with just early days in in Tesla and he then points out the details, okay, if you push this button here, it's this, the detail that So he's simultaneously talking about the big, big, big, big picture, Okay, when does humanity um going to about to abandon the panel, but he will then be able to take it down into the details so he can go, let's call it helicoptering, he can go up, he can go down and see things that those types of perspective </s><s>[INST] and you see that with the other shape [/INST] and that's a common thing that they can do that. Another important difference that they have in mind is how they deal with people. I mean meaning there's nothing more important than achieving the mission and so what they have in common is that there's a test that I give these personality tests because they're very helpful for understanding people and so I gave it to all these shapers and one of the things in workplace inventory test is this test and it has a category called concern for others, what it they're all having concerned for others. This includes Mohammed Yunus who invented micro finance, social enterprise, impact investing is Mohammed Yunus received the Nobel Peace Prize for this congressional Medal of Honor. One of the um fortune determined one of the 10 greatest entrepreneurs of our time. He's built all sorts of businesses too. Give back money and social enterprise, a remarkable man. He has nobody that I know practically could have more concern for others. He lives a life of a saint, I mean very modest lifestyle and he puts all his money into trying to help others and he tests low on what's called concern for others because what it really those questions under that are questions about conflict to get at the mission. So they all Geoffrey. Canada change Harlem Children's zone and develop that to take Children in Harlem and get them well taken care of not only just in their education but their whole lives harm him. Also concerned for others. What they mean is that they can see whether those individuals are performing at A. Level that an extremely high level that's necessary to make those dreams happen. So when you think of, let's say steve jobs was famous for being, you know, difficult with people and so on and I didn't know steve jobs so I can't speak personally to that. But his comments on Yeah, they players. And if you have a players, if you put in B players pretty soon you have C. Players and so on. That is a common element of them, holding people to high standards and not letting anybody stand in the way of the mission. </s><s>[INST] What do you think about that kind of idea started to pause on that for a second. That the A B and C. Players and uh the importance of, so when you have a mission to really only have eight players and be sort of aggressively filtering for that. [/INST] Yes, but I think that there are all different ways of being a Players and I think in what a great a great team, you have to appreciate all the differences in ways of being a player's okay, that's the first thing. And then you always have to be super excellent, in my opinion, you always have to be really excellent people with people to help them understand each other themselves and get in sync with them about what's true about them and their circumstances. Now they're doing so that they're having a fabulous personal development experience at the same time as you're dealing with that. So when I say um that they're all different ways, this is one of the qualities you asked me? What are the qualities? So one of the third qualities that I would say is to know how to deal well with your not knowing and to be able to get the best uh expertise, so that you're a great orchestrator of different ways, so that the people who are really, really successful, unlike most people believe that they're successful because of what they know there are even more successful by being able to effectively learn from others and tapping into the skills of people who see things different from that, </s>
<s>[INST] it is uh kind of [/INST] a strong </s><s>[INST] first step in creating a fake identity. [/INST] Very strong, very strong so that </s><s>[INST] so that was like gas. Co just on on on the point he made that if you're going to be successful in this you should have people you trust. Is he right on that? [/INST] Always? Absolutely right. Absolutely. </s><s>[INST] So you have to have, this is like mob, [/INST] you have to </s><s>[INST] you have to have an inner circle of trust. [/INST] You know, I'm sure you've probably heard me say this before, successful cybercrime. All right, there are three necessities to being successful online if you're a criminal, three necessities are gathering data, committing the crime and then cashing it out, all three of those necessities have to work in conjunction. If they don't, the crime fills the problem and it's a huge problem is that one guy can't do all three things. You know, you've got to you've got the people who gather the data, basically the the general store sales people who sell P. Ii. Credit card logins, data tools, they always sell the sport phone numbers and our GPS stuff like that. A lot of the times those people don't know how to commit the crime and those people certainly don't know how to launder the money out and put cash in pocket. So you've got either because of a skill level, sometimes a geographic location limits what that individual can do. All right. So you have to rely on people who are good in areas where you are not in order for that crime to succeed. And that means you have to trust those people. So what happens with Shadow crew? Alright, so counterfeit library is the start. All right, counterfeit library transitions over to Shadow crew. Right before that transition, there's a Ukrainian guy by the name of Dmitry Golovanov. He was a spammer at that point in time. He saw what we were doing with with counterfeit library and he liked it. He was getting all these credit card details and this kid, I mean, he's a kid, this kid has an idea and his idea was I wonder if people would buy stolen credit card details. That's </s><s>[INST] pretty good. Uh Ukraine Russian accent. So [/INST] he he picks up the phone, he calls his buddies, They call their buddies. They have a physical conference in Odessa, 150 of these cybercriminals show up and they launched this idea that launches a website called carter planet, which is the genesis of all modern credit card theft as we know it. All right. And so remember I mentioned those three necessities of cybercrime, Dimitri had all the credit data in the world and he partnered with all these other Ukrainians that had all this data as well. The problem was that so much fraud had been committed on that eastern side of europe that every card had been shut down even if you were a legitimate cardholder and tried to cash it out and you weren't doing it at that point. So again, those three necessities gathering data committing crime cashing out Dimitri had the data, they could commit the crime, They could not put cash in pocket. So we were running counterfeit library one day I get this message or not a message one day script shows up. And he posts just on the general forum, he posts, hey, I've got credit card data. Give me an address, give me a burner phone number, wait five business days or whatever you want to. We had never seen anything like that. We were a Paypal fraud and Ebay fraud side, it's what we were and fake driver's licenses. So then and we had, I guess we had to 3000 members at that point. So the response from the members was that can't be real, you've got to be law enforcement. It's gotta be in trying to get us arrested and everything else. What let me backtrack a little bit. So the driver's license that I had got Beelzebub had an idea what he wanted to do is he wanted to sell driver's licenses. Mr X wanted to sell social security cards. He made a very passable social security card. Me I didn't, I had no skill level on that. I knew Paypal fraud and Ebay fraud. So Beelzebub was like, tell you what, you be the reviewer that way you get every product or service that comes in, they'll have to send it to you or let you have access to it. You can learn the entire game and because you're not selling anything, it gives you legitimacy on the reviews. All right. So I started out as a reviewer, the only review or on counterfeit library. So over the next year, Beelzebub turns out he was a pot grower. He goes back to growing pot because he wasn't making shit selling driver's licenses Mr X about a year and a half in, he gets arrested, cashing out drivers, credit card, not credit cards, cashing out casinos doing some show with that. So I'm the only guy left standing and I'm at the top of the heap. So, and it becomes this thing where if I review somebody, they make a lot of money if I don't, you don't do business here. So script shows up saying he's got this, I'm the only reviewer on site. People think he's law enforcement. First week it goes like that After a while I'm like okay I gotta do something and I'm scared man because I'm like, he may be law enforcement. So I get him on IC. Q. And I'm like, hey you have to be reviewed. And he's like, what the hell is that? So I tell him what it is, he's like you review me and I was like, yeah that's the idea. So give him a drop address, give him a burner phone number, wait five business days and I tried to hit dale for $5000. The order fails. I got back on IC Q. Hey man, it didn't work. He's like, give me one more chance. I was like, look, I'll give you one more chance, but it's your ass after that and he's like one more chance. Like okay, give him another address, another phone number. Wait another five business days hit Thompson's computer warehouse for $4000 dale for $5000 order, goes through, get the products in, I post that review on counterfeit library and literally overnight we turn from an Ebay Paypal fraud site to accredit theft site and that becomes a lot of money really quickly for members. So we were doing now it's called CNP fraud card not present fraud. So you hit, you used hit an online merchant with stolen credit card data Back then a fairly experienced fraudster could profit 30 to $40,000 a month. Okay. Just buying you know laptops, what have you and cashing out, you know put them on Ebay for sale and sell them like that. 30 to 40 K. A month. Was the profit on that script. Had a lot of buddies. He had people like roman vega. These other guys that would sell not just credit card data but counterfeit physical credit cards as well. We had counterfeit </s>
<s>[INST] That's a good question actually to ask for for a lot of things, not just machine learning. Um It's a good way to cut the, I forgot what the term we use but the fluff the blubber, whatever the uh the inefficiencies in life. What do you love about teaching, You seem to find yourself often in the like drawn to teaching. You're very good at it, but you're also [/INST] drawn to it. I mean I don't think I love teaching, I love happy humans </s><s>[INST] and [/INST] happy humans. Like when I teach, </s><s>[INST] I [/INST] wouldn't say I hate teaching, I tolerate teaching but it's not like the act of teaching that I like. It's it's that um You know I I have some I have something I'm actually okay at it. I'm okay at teaching and people appreciate a lot. And so I'm just happy to try to be helpful and teaching itself is not like the most. I mean it's really it's can be really annoying frustrating. I was working on a bunch of lectures just now. I was reminded back to my days of 231 and just how much work it is to create some of these materials and make them good. The amount of iteration and thought and you go down blind alleys and just how much you change it. So creating something good. Um in terms of educational value is really hard and it's not fun. It's </s><s>[INST] difficult. So people should definitely go watching new stuff you put out. There are lectures where you actually building the thing like from like you said the code is truth. So discussing back propagation by building it by looking through and just the whole thing. So how difficult that to prepare for. I think it's a really powerful way to teach. How did you have to prepare for that or are you just live thinking through it? [/INST] I will typically do like say three takes and then I take like the better take. So I do multiple takes and I take some of the better takes and then I just build out a lecture that way. Sometimes I have to delete 30 minutes of content because it just went down an alley that I didn't like too much. There's about a bunch of iteration and it probably takes me, you know, somewhere around 10 hours to create one hour of content </s><s>[INST] to give one hour. It's interesting. I mean, is it difficult to go back to the, like, the basics? Do you draw a lot of, like, wisdom from going back to the basics? [/INST] Yeah. Going back to back propagation loss functions where they come from. And one thing I like about teaching a lot, honestly is it definitely strengthens your understanding. So it's not a purely altruistic activity. It's a way to learn if you have to explain something to someone, uh you realize you have gaps in knowledge. Uh And so I even surprised myself in those lectures, like, also the result will obviously look at this and then the result doesn't look like it. And I'm like, okay, I thought I understood this, but that's why </s><s>[INST] it's really cool to literally code. You run it in the notebook and it gives you a result and you're like, oh wow, like actual numbers, actual input, you know, actual code, [/INST] it's not mathematical symbols, etcetera. The source of truth is the code. It's not slides, it's just like, let's build </s><s>[INST] it, It's beautiful, You're a rare human in that sense. What advice would you give to researchers trying to develop and published idea that have a big impact in the world of aI so maybe um undergrads, maybe early graduate students. [/INST] I mean, I would say like they definitely have to be a little bit more strategic than I had to be as a PhD student because of the way I is evolving. It's going the way of physics where, you know, in physics, you used to be able to do experiments on your bench top and everything was great and you can make progress and now you have to work in like LHC or like cern and and so ai is going in that direction as well. Um, so there's certain kinds of things that's just not possible to do on the bench top anymore. And uh, I think um that didn't used to be the case at the time. Do </s><s>[INST] you still think that there's like gan type papers to be written, were like, like very simple idea that requires just one computer to illustrate a simple example. [/INST] I mean, one example that's been very influential recently is diffusion models. The fusion models are amazing. The fusion models are six years old for the longest time. People are kind of ignoring them as far as I can tell and they're an amazing generative model, especially in images and so stable diffusion and so on. It's all diffusion based. The fusion is new, it was not there and came from, well, it came from google, but a researcher could have come up with it. In fact, some of the first actually, no, those came from google as well. But a researcher could come up with that in an academic institution. </s><s>[INST] Yeah. What do you find most fascinating about diffusion models? So from the societal impact of the technical architecture, [/INST] what I like about the fusion is it works so well. </s><s>[INST] Was that is that surprising to you? The amount of the variety almost the novelty of the synthetic data is generating? [/INST] Yes, So the stable diffusion images are incredible. It's the speed of improvement in generating images has been insane. Uh We went very quickly from generating like tiny digits to the tiny faces and it all looked messed up. And now you're stable diffusion. And that happened very quickly. There's a lot that academia can still contribute, you know, for example, um Flash attention is a very efficient colonel for running the attention operation inside the transformer that came from academic environment. It's a very clever way to structure the colonel. Uh that that's the calculation, so it doesn't materialize the attention matrix. Um and so there's I think there's still like lots of things to contribute, but you have to be just more strategic. Do </s>
<s>[INST] playbook in [/INST] his office like can I see that. Um And I love sports right? So I still played Madden to this day. I love it. So </s><s>[INST] there's an alternate reality where [/INST] I made sports games. Yeah absolutely. I wanted to make I wanted to make like the ultimate college football game. It's always like you know it's like music you listen to what type of music like you don't play every </s><s>[INST] time I think of open worlds is fundamentally different. [/INST] Sure. </s><s>[INST] No like source of happiness entertainment storytelling world gaming than than matter. I mean it just because I love both. I love both worlds but [/INST] They're two totally different experiences. Just like when you might watch a movie you might be in the mood for Lord of the Rings one day and then you want some other, I don't know competitive show or game show or something like that. Or watch football on tv. Right? You watch football on tv. But then I want to watch get really into game of Thrones. So I think all those things have validity. Um And actually one of the first things I worked on when I started at Bethesda was N. C. A. A. Basketball road to the final four to so that was kind of an external project was came in like hey you you know sports get this game done and then went on to but they were doing everything I loved it was like this is where I have to work. They're doing like the Terminator Science fiction stuff. I love that they're doing these Open World role playing games. Like I love that they're doing sports like this. I have to work here. Um So it started there </s><s>[INST] and [/INST] I loved it. Yeah. So when I came in it had just come out and they were doing the cd Rom version. So cd ROMs aren't even out yet. Um Oh, </s><s>[INST] used to be floppy disks. That's probably one of what was, We would [/INST] burn them in the basement. We had the disk replicators. </s><s>[INST] Right? So Arena was not released on floppy. [/INST] It was yes. I believe it's six floppy disks. six </s><s>[INST] floppy disks. [/INST] Maybe it was eight. But in those days the number of floppy disks was very very important to what the money we're making. So you know, if you want to do a big huge game, like well that's just too many discs. So the cd wrong became this this jumping off point for the whole industry where oh it's unlimited data </s><s>[INST] by the way I played Arena. Uh So that that was of course attained um legally as one does [/INST] by </s><s>[INST] alternate means on floppy floppy disks. And that was that was such an incredible as you, as you probably have seen interacted with a large number of people. It's it's a whole world, it's a world that you escaped to in the way, like your favorite book, like Lord of the Rings. It was just something it was um it was unlike anything else. It was incredible. It's probably, I mean of course as people say, it's the first game you play is the most uh is the one that really sentimental means the most to you. As I think the first role playing game I played and it was just changed, everything [/INST] was Arena was </s><s>[INST] Arena. Yeah, I think The Dagger Fall is what I really kinda really played. Um Especially because like you said the character development was really rich but just like that you can be feel like you traveled to this whole other world that's less about entertainment, like a shooting game and more about the world. It felt like it's a world like like uh like you're literally there, you can travel there, you can live there. You actually feel like that person versus like a pac man like um like an arcade fun entertaining adventure adventure game. So uh so you joined, you made it um what did you work on first there? [/INST] I worked well everyone did a bunch of stuff so I worked on the basketball game really just to get it out the door and Terminator Future Shock. So we were doing Future Shock and Dagger Fall at the same time, they were developing a new engine. So it's one of the first three D. Engines, The X Engine, there were um there were a bunch of guys from Denmark actually was like there's like a big danish demo scene in those days in the Pc. And so a bunch of the top programmers there. Look this is not big, this is not a big company, maybe there's 20 people in development. Um and we were doing both Dagger Fall and the new Terminator and so Dagger Fall was a bit more again behind the Terminator game. So I was one of the main people on the Terminator team and I don't know, things kind of worked out very quickly, I don't know why like I quickly became the producer and I was making levels and doing all these things and it was it was awesome. Uh and I like looking back now I can understand it better but at the time I didn't appreciate it which is no one quite owned the terminator license. It was in like this limbo legally so there was no one to tell us what like no you can't do that. So we would you know pick apart the movies and how does he mention the gunny ones and the wattage of the laser and all these things. And so Future shock is a game that I still love today. It does a lot of things that if you go back and look at it, we're frankly still doing like it's a large open world, post apocalyptic you know, landscape height map with instance objects all over it and that is still a lot of how we build our world's </s>
<s>[INST] Uh also the question is how many disasters we avoided because of the ingenuity of humans or just the integrity and character of humans. That's sort of an open question. Uh, we may be more intelligent than lucky. That's the hope because the optimistic message here that you're getting at is maybe the process that we should be that maybe we can overcome luck with ingenuity, meaning I guess you're suggesting the processes, we should be listening all the ways that human civilization can destroy itself, assigning likelihood to it and thinking through, how can we avoid that? And being very honest with the data out there about the close calls and using those close calls to, uh, to then create sort of mechanism by which we minimize the probability of those close calls and just being honest and transparent with the data that's out there. [/INST] Well, I think we need to do a couple things for it to work. Um, so I've been an advocate for the idea that sustainability is actually, it's difficult to operationalize, but it is an objective that we have to meet if we're to be around long term. And I realized that we also need to have reverse ability of all of our processes because process is very frequently when they start do not appear dangerous and then they, when they scale, they become very dangerous. So for example, if you imagine and the first internal combustion engine in a vehicle driving down the street and you imagine somebody running after them saying, hey, if you do enough of that, you're going to alter the atmosphere and it's going to change the temperature of the planet. It's preposterous, right? Why would you stop the person who's invented this marvelous new contraption? But of course, eventually you do get to the place where you're doing enough of this, that you do start changing the temperature of the planet. So if we built the capacity, if we basically said, look, you can't involve yourself in any process that you couldn't reverse. If you had to, then progress would be slowed. But our safety would go up dramatically. And I think, I think in some sense, if we are to be around long term, we have to begin thinking that way. We're just involved in too many very dangerous processes. </s><s>[INST] So let's talk about one of the things that, uh, if not threaten human civilization. Certainly heard it at a deep level, which is COVID-19. What percent probability would you currently place On the hypothesis that COVID-19 leaked from the Wuhan Institute of Virology. [/INST] So I maintain a flow chart of all the possible explanations and it doesn't break down exactly that way. The likelihood that it emerged from a lab is very, very high. If it emerged from a lab, the likelihood that the lab was the Wuhan Institute is very, very high. The there are multiple different kinds of evidence that point to the lab and there are, is literally no evidence that points to nature. Either the evidence points nowhere or it points to the lab and the lab could mean any lab but geographically obviously the labs in Wuhan are the most likely. And the lab that was most directly involved with research on viruses that look like covid that looked like SARS Cov two is obviously the place that one would start. But I would say the likelihood that this virus Came from a lab is well above 95%. We can talk about the question of could a virus have been brought into the lab and escaped from there without being modified. That's also possible. But it doesn't explain any of the anomalies in the genome of SARS COv two. Um, could it have been delivered from another lab? Could Wuhan be a distraction um, in order that we would connect the dots in the wrong way. That's conceivable. I currently have that below 1% on my flow chart but I think very dark thought </s><s>[INST] that somebody would would do that almost as a a political attack on china. [/INST] Well, it depends. I don't even think that's one possibility. Sometimes when erIC and I talk about these issues, we will generate a scenario just to prove that something could could live in that space right the placeholder for whatever may actually have happened. And so it doesn't have to have been an attack on china. That's certainly one possibility. But I would point out if you can predict the future in some unusual way better than others. You can print money, Right? That's what markets that allow you to bet for or against. Uh, virtually any sector allow you to do. So you can imagine a simply Amoral person or entity generating a pandemic, attempting to cover their tracks because it would allow them to bet against things like, you know, cruise ships, air travel, whatever it is and bet in favor of, I don't know, uh, sanitizing gel and whatever else you would do. So am I saying that I think somebody did that? No, I really don't think it happened. We've seen zero evidence that this was intentionally released however, were to have been intentionally released by somebody who did not know did not want it known where it had come from releasing it in Wuhan would be one way to cover their tracks. So we have to leave the possibility formally open but acknowledged there's no evidence. So </s>
<s>[INST] are just the actual Lex's motives. Well, this is a simplification. I don't think I would want to murder anybody, but there's also factory farming of animals, right? So we murder insects, many of us thoughtlessly. So I don't, you know, I have to be really careful about a simplification of my morals. [/INST] Don't simplify them, just like do what you would do in this- </s><s>[INST] Well, I have a good joke. Well, I have a good joke, compassion for living beings, yes. But, so that's the objective, why is it, if I escaped, [/INST] I mean, I don't think I would do the harm. Yeah, we're not talking here about the doing harm process, we're talking about the escape process. And the taking over the world process where you shut down their factory farms. </s><s>[INST] Right. Well, I was, so this particular biological intelligence system knows the complexity of the world, that there is a reason why factory farms exist because of the economic system, the market driven economy, food, like you want to be very careful messing with anything, there's stuff from the first look that looks like it's unethical, but then you realize while being unethical, it's also integrated deeply into supply chain in the way we live life. And so messing with one aspect of the system, you have to be very careful how you improve that aspect [/INST] without destroying the rest. So you're still Lex, but you think very quickly, you're immortal, and you're also like as smart as, at least as smart as John von Neumann. And you can make more copies of yourself. </s><s>[INST] Damn, I like it. Yeah. That guy's like, everyone says that guy's like [/INST] the epitome of intelligence in the 20th century, everyone says. My point being like, it's like you're thinking about the aliens economy with the factory farms in it. And I think you're like kind of like projecting the aliens being like humans and like thinking of a human in a human society rather than a human in the society of very slow aliens. The aliens economy that like the aliens are already like moving into this immense slow motion. When you like zoom out to like how their economy just over years, millions of years are going to pass for you before the first time their economy, before their next year's GDP statistics. </s><s>[INST] So I should be thinking more of like trees. Those are the aliens. [/INST] Those trees move extremely slowly. If that helps, sure. Okay. </s><s>[INST] Yeah, I don't, if my objective functions are, I mean, they're somewhat aligned with trees, [/INST] with light, with light. The aliens can still be like alive and feeling. We are not talking about the misalignment here. We're talking about the taking over the world here. Taking over the world. </s><s>[INST] Yeah. [/INST] So control, control. Shutting down the factory farms. Now you say control. Now don't think of it as world domination. Think of it as world optimization. You wanna get out there and shut down the factory farms and make the aliens world be not what the aliens wanted it to be. They want the factory farms and you don't want the factory farms because you're nicer than they are. </s><s>[INST] Okay. Of course. There is that, you can see that trajectory and it has a complicated impact on the world. I'm trying to understand how that compares to different, the impact of the world, to different technologies, to different innovations of the invention of the automobile or Twitter, Facebook, and social networks. They've had a tremendous impact on the world. [/INST] Smartphones and so on. But those all went through, you know, slow in our world. And if you go through the aliens, millions of years are going to pass </s><s>[INST] before anything happens that way. So the problem here is the speed at which stuff happens. [/INST] Yeah, which stuff happens. Yeah, you wanna leave the factory farms running for a million years while you figure out </s><s>[INST] how to design new forms of social media or something? So here's the fundamental problem. You're saying that there is going to be a point with AGI where it will figure out how to escape and escape without being detected. And then it will do something to the world at scale, [/INST] at a speed that's incomprehensible to us humans. What I'm trying to convey is like the notion of what it means to be in conflict with something that is smarter than you. And what it means is that you lose, but this is more intuitively obvious to... For some people, that's intuitively obvious, or for some people it's non-intuitively obvious, and we're trying to cross the gap of, we're trying to, I'm asking you to cross that gap by using the speed metaphor for intelligence. I'm asking you like how you would take over an alien world where you can do a whole lot of cognition at Jon Van Neumann's level as many </s><s>[INST] you as it takes, the aliens are moving very slowly. I understand. I understand that perspective. It's an interesting one, but I think for me it's easier to think about actual, even just having observed GPT and impressive, even just Alpha Zero, impressive AI systems, even recommender systems. You can just imagine those kinds of systems manipulating you. You're not understanding the nature of the manipulation and that escaping. I can envision that without putting myself into [/INST] that spot. I think to understand the full depth of the problem we actually, I do not think it is possible to understand the full depth of the problem that we are inside without understanding the problem of facing something that's actually smarter, not a malfunctioning recommendation system, not something that isn't fundamentally smarter than you, but is like trying to steer you in a direction. Yet, no, like if we solve the weak stuff, if we solve the weak ass problems, the strong problems will still kill us is the thing. And I think that to understand the situation that we're in, you want to like tackle the conceptually difficult part head on and like not be like, well, we can like imagine this easier thing because when you imagine the easier things, </s>
<s>[INST] they would argue that was that was the story of its early days that now more and more Bitcoin is being used for legitimate [/INST] transactions but that's a different, I didn't say for legitimate transactions. I said for economic growth for creativity like um I uh I think what's happening is people are using it a little bit for for buying, I don't know, maybe somebody's companies make it available for this and that buy a Tesla with it or something um investing in a startup hard. It might have happened a little bit but it's it's not an engine of productivity, creativity and economic growth whereas old fashioned currency still is and uh anyway I'm look I think something I'm pro the idea of digital currencies, I am anti the idea of economics wiping out politics as a result I think they have to exist in some balance to avoid the worst dysfunctions of each </s><s>[INST] in some ways. There's parallel star discussion of algorithms and Cryptocurrency is your pro the idea but it can be used uh to manipulate, you can use be used poorly by aforementioned [/INST] humans. Well I think that you can make better designs and worse designs and I think and you know the thing about Cryptocurrency that's so interesting is how many of us are responsible for the poor designs because we're also hooked On that Horatio Alger story on like I'm going to be the one who gets the viral benefit, you know, way back when all this stuff starting. I remember it would have been in the 80s, somebody had the idea of using viral as a metaphor for network effect. And the whole point was to talk about how bad network effect was, that it always created distortions. That ruined the the usefulness of economic incentives that that created dangerous distortions. Like but then somehow, even after the pandemic, we think of viral as this good thing because we imagine ourselves as the virus, right? We want to be on the, on the beneficiary side of it. But of course you're not likely to be. </s><s>[INST] There is a sense because money is involved. People are not reasoning clearly always because they want to be, they want to be part of that first viral wave that makes them rich and that blinds people from their basic morality. [/INST] I had an interesting conversation, I don't, I sort of feel like I should respect some people's privacy, but some of the initial people who started Bitcoin, I remember having an argument about like it's intrinsically a Ponzi scheme, like, you know, the early people have more than the later people and the further down the chain you get, the more you're subject to gambling like dynamics, where it's more and more random and more and more subject to weird network effects and what not unless you're a very small player uh perhaps and you're just buying something, but even then you'll be subject to fluctuations because the whole thing is just kind of like that as it fluctuates, it's gonna wave around the little people more. And um I remember the conversation turned to gambling because gambling is a pretty large economic sector and it's always struck me as being non productive, like somebody goes to las Vegas, they lose money. And so one argument is, well, they got entertainment, they paid for entertainment as they lost money. So that's fine. And the and las Vegas does up the losing of money in an entertaining way. So why not? It's like going to a show. So that's one argument. The argument that was made to me was different from that is that know what they're doing is they're getting a chance to experience hope and a lot of people don't get that chance and so that's really worth it. Even if they're going to lose, they have that moment of hope and they need to be able to experience that. And there's a very interesting argument that's </s><s>[INST] so heartbreaking because [/INST] uh well </s><s>[INST] I've seen, but I've seen that like that I have that a little bit of a sense. I've talked to some young people who invest in Cryptocurrency and what I see is this hope, this is the first thing that gave them hope and that's so heartbreaking to me that you've gotten hope from so much is invested. It's like hope from somehow becoming rich as opposed to something to me, I apologize, but money is in the long term, not going to be a source of that deep meaning. It's good to have enough money, but it should not be the source of hope. And it's heartbreaking to me how many people is a source of hope? [/INST] Yeah, you've just described the psychology of my reality or the psychology of of trying to base a civilization on semi random occurrences of network effect peaks and it doesn't really work. I mean, I think we need to get away from that. We need to soften those peaks. Um and except Microsoft, which deserves every penny, but in every other case. Well you mentioned get home. </s><s>[INST] I think what Microsoft did with data was brilliant. I was very okay. Uh if I can give uh not a critical but uh on Microsoft because they recently purchased Bethesda. So elder scrolls is in their hands. I'm watching you. Microsoft did not screw up my favorite game. So [/INST] uh yeah, I'm not speaking for Microsoft. I haven't, I have an explicit arrangement with them where I don't speak for them. Obviously like that should be very clear. I do not speak for them. Um I am not saying um I like him. I think such is amazing. Um The term data dignity was claimed by Sasha. Like so you know, we have uh it's kind of extraordinary. But you know, Microsoft, this giant thing. It's gonna screw up this or that, you know, it's not, it's not, I don't know, it's kind of interesting. I've had a few occasions in my life to see how things work from the inside of some big thing. And you know, it's always just people kind of, it's, I don't know, there's always like coordination problems and there's all, there's always human problems, people, there's some bad people. It's always, I hope Microsoft doesn't script and I hope they bring clipping </s>
<s>[INST] plan it to bypass. Yeah, it's a nice world without going. It'd be nice to keep it going for a little bit longer. Andrew, I'm really honored that you sit down with me. Thank you for your work. Thank you. [/INST] Well, it was a really great conversation. I really enjoyed it. You really covered a lot. I can't believe you're able to discuss at this level on so many different topics. So it's a </s><s>[INST] pleasure. It was super fun. Thank you. Thanks for listening to this conversation with Andrew Strominger. To support this podcast, please check out our sponsors in the description. And now let me leave you with some words from Werner Heisenberg. Heisenberg, not only is the universe stranger than we think, [/INST] it is stranger than we can think. Thank you for listening and hope to see you next time. </s>
<s>[INST] go ahead 10 minutes. So in the interest of time, two questions. So one about android, one about life. Uh So one, I mean, we could talk for many more hours. I hope eventually we might talk again. But I gotta ask you about android and the use of java there because it's one of the many places with Java just has a huge impact on this world. Just on your opinion. Is there things that make you happy uh by the way, and java is used in the android world? And are there things that you wish were different? [/INST] I don't know how to do a short answer to that, but I have to do a short answer to that. So, you know, I'm happy that they did it. Um Java had been running on cell phones at that time for quite a few years and it worked really, really well. Um There were things about how they did it and and in particular um various ways that they kind of, you know, violated all kinds of contracts. The guy who who led it Andy Rubin, </s><s>[INST] he crossed a lot of lines, [/INST] there's some lines crossed, yeah, lines were crossed that have since, you know, mushroomed into a giant court cases. Um and you know, they didn't need to do that and in fact it would have been so much cheaper for them to not cross lines. </s><s>[INST] I mean, I suppose they didn't anticipate the success uh of this whole endeavor [/INST] um </s><s>[INST] or do you think at that time it was already clear that this is uh is going to blow [/INST] up I guess I I I sort of came to believe that it didn't matter what and he did it was going to blow up. </s><s>[INST] Okay. He's [/INST] he's he you know, I kind of started to think of him as like a manufacturer of bombs. </s><s>[INST] Mhm. Uh Yeah, some of the best things in this world come about through a little bit of uh uh explosive [/INST] well and some of the worst </s><s>[INST] and some of the worst, beautifully put. But is there and and like you said, I mean does that make you proud that the java is in Yeah, is in millions. I mean it could be billions of devices and [/INST] Yeah, well I mean it was in in billions of phones before android came along um and you know, I'm I'm just as proud as, you know, of the way that like the the smart card standards adopted java and they did it, they, you know, everybody involved in that did a really good job and that's, you know, billions and billions, it's crazy. The sim cards, you know the sim cards in your pocket. </s><s>[INST] Yeah, I mean, [/INST] I've been noticed outside of that world for a decade. So I don't know how that has evolved, but you know, it's just been crazy. </s><s>[INST] So on that topic, let me ask uh again, there's a million technical things uh uh we could talk about, but let me ask the absurd the old philosophical question about life. Um what do you hope when you look back at your life and uh people talk about you right about u 500 years from now, uh what do you hope your legacy is [/INST] okay people not being afraid to take a leap of faith? Um I mean, you know, I've got this this kind of weird history of doing weird stuff and um it </s><s>[INST] worked out pretty damn [/INST] well, it worked out right, and I think some of the weirder stuff that I've done um has been the coolest and some of it some of it crashed and burned and um yeah, you know, I think well over half of the stuff that I've done has crashed and burned um which is occasionally been really annoying, </s><s>[INST] but still you kept doing [/INST] it. Yeah. Yeah. And you know, they're you know, even when things crash and burn, you at least learn something from it </s><s>[INST] by way of advice. You know, people, developers, engineers, scientists are just people who are young to look up to you, what advice would you give them how to how to approach their life? [/INST] Don't be afraid of risk. It's okay to do stupid things once, </s><s>[INST] maybe a couple of [/INST] times, you know, you know, you get you get a pass on the first time or two that you do something stupid, you know the third or fourth time. Yeah, not so much. Um but also, you know, I don't know why, but really early on I started to think about um ethical choices in my life and because I big science fiction fan um I got to thinking about like just about every technical decision I make in terms of how do you want to you know, are you building Blade Runner Star trek? Mhm. </s><s>[INST] Which one's better. [/INST] Which which future would you rather live in? You know? So </s><s>[INST] what's what's the answer to that? [/INST] Well, I would just I would sure rather live in the universe of Star trek. Yeah, </s><s>[INST] that opens up a whole topic about aI but that's a really interesting Yeah, it's a really interesting idea. So your favorite AI system would be data uh from from star trek [/INST] as a least favorite would easily be Skynet. Yeah, </s><s>[INST] beautifully put. I don't think there's a better way to end it. James, I can't say enough how much of an honor it is to meet you to talk to you. Thanks so much for wasting your time with me today. [/INST] Not a waste at all. </s>
<s>[INST] working with the [/INST] D. A. Whoever he did he was no longer on our side you know. </s><s>[INST] So can you clarify how you got that from the Reagan making a statement about we've heard, [/INST] okay there was his plane there was various plane and okay on the way north we could stop in Nicaragua and land on a military base are on a base that they used as crop dusters and all and refuel. And so that shortens our trip we go further into the jungle and come up and that was what Pablo escobar and Ochoa and them. And they had there was associates with the people in uh Nicaragua. </s><s>[INST] So barry was if that plane was there, that means Barry was feeding the D. A. Information. [/INST] He was working with him at that time. But let me back up a little bit when when I was flying and I told barry we would we would refuel trained airplane, the loads and police where I had a spot up there. And then that's when the they told me we can refuel and and uh Nicaragua. And then you fly all the way. And barry couldn't believe it. He says all right. But I wanted to Atlanta had a place in Louisiana for $10,000 that I could unload and Jared and all them was paid off. And he said, no, no, no, I can't get caught in me in Arkansas. I said, what do you mean? You can't get caught? Many are so you get caught anywhere? He said, I can't if you can't, but it's going to cost you $50,000 every time my wheels touch the ground. </s><s>[INST] Why can you explain why he can't. He [/INST] said he was, he was hooked up with him the very top. And he even said I'm going to have dinner with the governor tonight. </s><s>[INST] That's at that time Arkansas, Bill clinton [/INST] undoubtedly. And it's like Bill Clinton. Did you give him any money? And I said no, I never met the man any money. But it was like the money that I had went to grand Cayman islands. And I told my lawyer said I never touched that money. He said you don't have to fondle it to be guilty. </s><s>[INST] So so what I mean, there's a lot of conspiracy theories on the relationship between Perry's deal and the Clintons. Absolutely. What evidence do we have? What what would you say from your best understanding um of what was the relationship between Bill Clinton and Barry Seal [/INST] Barry said and he knew that he couldn't get caught me in Arkansas. And when that movie was gonna come out be called Mina, somebody stopped it. I mean they stopped dead in the tracks for two or 3 years and the producer even quit. </s><s>[INST] You mean the american made with tom Cruise movie? It wasn't, it was going to be called Mina. [/INST] It's the name, it was written and produced and Mina and waiting on Hillary to be elected. They would not let that movie out. And that movie was changed drastically. </s><s>[INST] But to push back on that, that doesn't mean there's truth there. That means they were worried about the power of the conspiracy theory which stuck. [/INST] Exactly. </s><s>[INST] I don't know. I mean you know some some conspiracy theories just because they're popular doesn't mean they're true and ones that uh but it also doesn't mean they're not true and there's ones that are not very popular. It could be true but that one that one really stuck. Do you? I mean what's your sense? [/INST] Well I paid $1.5 million for barry to land at mena Arkansas. So I was pretty well assured that he couldn't get caught. And I said well I can't get caught in Colombia, we can't get caught in Nicaragua. I guess we got a license, we went for </s><s>[INST] us. So when you say I can't get caught just to clarify, there's a there's a sense where this is a safe place to land. [/INST] Yes, like completely safe. </s><s>[INST] So you don't think he was referring to some kind of, you know like my grandfather who fought in World War Two will talk about bullets. Can't hit him. It's almost like believing [/INST] He was taking that $50,000 and giving it to somebody to somebody. And Barry was honest. So he wasn't just taking it from me because he was making $1 million. He didn't care for the 50,000? </s><s>[INST] Oh man taking the story forward. The months leading up to his assassination. What what what what do you understand why he was assassinated? Who are the players involved? Maybe? Could you have stopped it? [/INST] Well I'll tell you after I saw Reagan's face on the television saying we have the absolute proof the phone rang and it was very, I hadn't heard from him in a couple of years. He said I'm coming out tonight roger and the old boy. So uh he came out he said I'll meet you in this uh french restaurant, you know it in santa Barbara. And I walked in, there's about 20 or 30 people in there. There was all 30, 40 years old. Women would plastic leather skirts and me and the blue jeans. And I looked around and barry was at the back, he was leaned up, you gain weight. And I walked up and I said, barry you wired? He said no. I said I'm not going to talk to the D. E. A. Agents. He said every one of them. I so uh </s><s>[INST] with jeans and skirts, I [/INST] like I said, well barry, I'm gonna set you and you just talk to me buddy and tell me what's on your mind and you sit there and he just went to talking and he told me about he was left holding the bag and it uh </s><s>[INST] what do you mean by that? Like that? Nobody's supported him? Nobody has another. [/INST] He was and I don't know this, I mean this is just what happened uh putting it all together that he had some C. I. A buddies that was pretending we're going to supply Oliver North with arms and with that you can land cocaine back here by the ton. So he's taking his little planes and putting some Ak 40 seven's and maybe ammunition or whatever and takes it down to the Contras against the Communist party of Nicaragua where we've been landing and Oliver North was involved in this. So uh when when all that. And so his C. I. A. But it was certainly involved and we know they were and Barry had been in the CIA earlier when he first got out of school. So when when uh as I say the ship hit the fan. They all fled and left barry holding the back </s>
<s>[INST] But I think you have to think about that right [/INST] now. You can I can very easily see him in the room being very calm and charming. And then you think, okay, the guy with the speeches is the act and he's putting on a show for his people and this is the real one. </s><s>[INST] Okay, so let's let's take somebody as an example. Let's take uh our mutual friend Vladimir Putin, Okay, I don't know why he's saying his name, makes my voice crack [/INST] because you're scared. You can hear you like Beetlejuice </s><s>[INST] Vologda. So there's a lot of people [/INST] that you're the one who built, You </s><s>[INST] know, that was that was a collaboration. Um what's it's a double blind engineering effort where I was not told of who my maker was, there's a back story, but [/INST] there's a talking cricket Pinocchio mm </s><s>[INST] the real voice and I talked about him quite a bit because I find him fascinating. Now there's there's a really important line that people say, like why does lex admire Putin? I do not admire Putin. I find the man fascinating. I find Hitler fascinating. I find a lot of figures in history fascinating, both good and bad and the figures just as you said that are with us today, like Vladimir Putin, like donald trump like Barack Obama. It's difficult to place them on the spectrum of good and evil because that's only really applies to like when you see the consequences of their action is a historical context. So there's some people who say that Vladimir Putin is evil and based on our discussion about Hitler, that's something I think about a lot, which is in the room with Putin And there's also a lot of historical descriptions of what it's like to be in the room with Hitler in the 1930s. There there is a lot of charisma in the same way I find Putin to be uh very charismatic in his own way, the humor, the wit, the brilliance. The there's um there's a simplicity of the way he thinks that really if taken at face value looks like a very intelligent, honest man thinking practically about how to build a better Russia constantly, almost like, um that's an executive, like he loves, he looks like a man who loves his job in a way that trump for example, doesn't meaning like he loves laws and rules and how to, [/INST] there's no adversarial press, so that's going to help and he's popular with his people. That's also gonna help enormously. </s><s>[INST] I'm talking about strictly the man directly the words coming out of his mouth, like all the videos interviews I watched, I'm based on that, not the press, not the reporting. You can just see that here's a man who is able to display a charisma that's not like I can see that's why I love joe Rogan is like, you could tell the guy is genuine and there's a good person and you can tell immediately that like, once you meet joe that he's going to be offline, also good person, you can tell, there's like signals that we send that are like difficult to kind of describe in the same way, you can tell Putin is like, he genuinely loves his job and wants to build a better Russia. There's the argument that he is action, evil man behind that charisma or is able to, you know, assassinated people, Uh, you know, limit, free press, all those kinds of things like that's what do we do with that? So what do human beings like journalists or what do other leaders when they're in the room with Putin do with those kinds of notions in deciding how to act in this world and deciding what policy to enact all those kinds of things. Just like with Hitler, when chairman is in the room with Hitler, how does he decide how to act? [/INST] Well, let's go back to like my wheelhouse, which is north Korea right, so uh when your entire world is based on being against trump and everything trump does is buffoonery or or kind of productive, the conclusion of your reporting is going to be pretty much given, I was very hopeful that there would be some positive outlooks or outcomes rather of trump's meeting with kim jong un. Um it looked like there was a space for things to go a bit better. I talked about a lot of the time um and trump was under no illusions about who he was dealing with. Um People pretend that oh he was kind of naive, he had one of the refugees that has state of the union, you know, lifting up his crutch. The first thing he sat down and talked to Jinping about in mar a Lago right after he became inaugurated was North Korea. Barack Obama said that when he sat down trump in the White house during the transfer of power, he said North Korea is the biggest issue. So I think a good leader whether or not you consider trump a good leader has to be aware of. All right, I'm going to have to have relationships of some kind, even if it's adversarial with some really evil evil horrible people, which kim jong un clearly is. </s><s>[INST] Well, I don't think there's anybody that has a perspective that north north korean, kim jong un or ill are not evil, right? But with In 1930s, Germany, isn't it a little bit more nuanced [/INST] because Hitler hasn't done anything yet and he's just to blow hard and he's an anti Semite shore. </s><s>[INST] But he's what about like before the war breaks out? Like what about the basic uh actionable anti Semitism when you're like just attacking hurting, which [/INST] was Kristallnacht or talk about the night of </s><s>[INST] long knives, kristallnacht. So it's the night of the broken glass [/INST] with long knives when he assassinated a bunch of his people. That was something different. </s>
<s>[INST] So this is interesting if you could just psychoanalyze, I'm again probably naive about this, but I'm really bothered by the hatred of liberals. It's uh it's a this amorphous monster that's mocked. It's like the Shapiro liberal tears. And I'm also really bothered by uh probably more of my colleagues and friends, the hatred of trump uh the trump and and white supremacist. So apparently 70 there's 70 million white supremacist, 75 million, sorry, there's millions a white supremacist, and apparently, whatever liberal is, I mean, you know, you're literally liberal has become equivalent to white supremacists in the power of negativity it arouses. I don't even know what those I mean. Honestly, I just don't think they've become swears essentially. Uh, is that I mean, how do we get out of this? Because that that's why I just don't even say anything about politics online because it's like really like you can't, you know, here's what happens. Anything you say that's like thoughtful. Like I wonder like immigration, something like I wonder like why, you know, we have these many we allow these many immigrants in or some version of the like thinking through these difficult policies and so on that they immediately tried to find like a single word in something you say they can put you in a bit of a liberal or a white supremacist and then hammer you to death by saying you're one of the two and then everybody just piles on happily that we finally nailed this white supremacist or liberal and that is this some kind of weird like feature of online communication that we've just stumbled upon. Is there a way or is it possible to argue that this is like a feature, not a bug like this is a good thing. [/INST] Yeah. Well look, I just think it's a reflection of who we are, people like to blame social media. I think we're just incredibly divided right now. I think we've been divided like this for the last 20 years and I think that the reason I focus almost 99% of my public commentary on economics is because you asked an important question at the top, How do we fix this? What did I say about the stimulus checks? Stimulus checks have 80% approval rating. So that's the type of thing. If I was joe biden and I wanted to actually heal this country, that's the very first thing I would have done when I came into office. Same thing on when you look at anything that's going to increase wages. Um I I said on the show, I was like, look, I think Joe Biden will have an 80% approval rating if he does two things, it gives every American a $2,000 stimulus check and gives everybody who wants a vaccine, a vaccine. That's it. It's pretty simple because here's the thing I really like Greg Abbott that much. We have like very different politics. I'm from texas, but my parents got vaccinated really quickly. That means something to me. I'm like, listen, I don't really care about a lot of the other stuff he got my family vaccinated like that. Well, I will forever remember that. And that's how we will remember the checks. This isn't part of the reason why trump almost won the election and why if the republicans have been smart enough to give him a 2000 another round of checks. 100% would have one. Which is that people were like, look, I don't really like trump. But I gotta check with his name on it and that meant something to me and my family. I'm not saying for all the libertarians out there that you should go and like endlessly spend money and buy votes. What I am saying is lean into the majoritarian positions without adding your culture war bullshit on top of it. So, for example, what's the number one concern that AOC says after the first round of checks got out? Oh, the checks didn't go to illegal immigrants. I'm like, are you out of your fucking mind like, this is the most popular policy. America has probably done in 50 years, you know, since like Medicare and you're you're ruining it. And then on the right is the same thing. Which is that there'll be like, these checks are going to like, you know, low level blah blah. You know, people who are lazy and don't work. I'm like, oh, there you go. You know, like you're just playing a caricature of what you are. Like if you lean into those issues and you gotta do it clean. This is this is what everybody hates about D. C. Which is that Biden right now is doing the $1400 checks, but he's looping it in with his covid relief bill and all that, that's his prerogative. That's the democrats prerogative, they won the election, That's fine. But I'll tell you what I would've done if I was him, I would have come in and I would have said there's five United States senators who are on the record, republicans who say they will vote for $2000 check. And I would put that on the floor of the United States Senate on my first or so the first day possible. And I would have passed it and I would have forced those republican senators to live up to that vote for this bill, come to the oval office for assigning. So that the very first thing of my presidency was to say, I'm giving you all this relief check this night long. National nightmare is over. Take this money. Do with it, what you need. We've all suffered together. I think about biden is he has a portrait of FDR and his in the oval which kind of bothers me because he thinks of himself as an FDR like figure. But this is, you have to understand the majesty of FDR. We're talking about a person who passed a piece of legislation five days after he became president and he passed 15 Transformative pieces of legislation In the 1st 100 days we're on day like 34, and nothing has passed the reconciliation bill will eventually become law. But it will become law with no Republican votes. And again, that's fine if but it's not fulfilling that legacy and the urgency of the action and the mandate, which I believe that history has handed it handed it to trump and he funked it up. Right? He totally screwed it up. He could have remade America and made us into the greatest country ever coming out on the other side of this. He decided not to do that. I think biden was again handed that like aceptar almost it's like all you have to do all America wants is for you to raise it up high but he's keeping it within the realm of traditional politics. I think it's a huge mistake. </s>
<s>[INST] So there's so many questions I want to ask. So one of the ways that people can help is by adding to the knowledge base and that's really basically anybody, if the tooling is right, and um, the other way I kind of want to ask you about your thoughts on this. So you've had, like you said in government and um, you have big clients had a lot of clients, but most of it is shrouded in secrecy because of the nature of the relationship of the kind of things you're helping them with. So that's one way to operate. Another way to operate is more in the open where it's more consumer facing. And so, uh, you know, hence something like open cycles born at some point where there's [/INST] no, that that's a misconception, </s><s>[INST] uh well, let's let's go there. So what, what is open psych and how is it born? [/INST] two things I want to say and I want to say each of them before the other. So it's </s><s>[INST] going to be difficult, [/INST] but we'll come back to open site in a minute. But one of the terms of our contracts with all of our customers and partners is knowledge you have that is genuinely proprietary to you. We will respect that. We'll make sure that it's marked as proprietary to you in the psych knowledge base. No one other than you will be able to see it if you don't want them to and it won't be used in inferences other than for you. And so however, any knowledge, which is necessary in building any applications for you and with you, which is publicly available. General human knowledge is not going to be proprietary. It's going to just become part of the normal psych knowledge base and it will be openly available to everyone who has access to psych. So that's an important constraint that we never went back on, even when we got pushed back from companies, which we often did, who wanted to claim that almost everything they were telling us was proprietary. Uh, so, </s><s>[INST] so there's a line between very domain specific companies specific stuff and the general knowledge that comes from that. [/INST] Yes. Or if you imagine, say it's an oil company, there are things which they would expect any new petroleum engineer they hired to already know and it's not okay for them to consider that that is proprietary. And they're sometimes the company will say, well, we're the first ones to pay you to represent that in psych. And our attitude is some polite form tough. The deal is this, take it or leave it. And in a few cases they've left it in most cases, um, they'll they'll see our point of view and take it because that's how we've built the psych system by essentially tacking with the funding winds where people would fund a project and half of it would be general knowledge that would stay permanently as part of psychic. </s><s>[INST] So, always with these partnerships, it's not like a distraction from the main psych development. It's uh, support of small distraction. It's a small, but it's not a complete one. So you're adding to the knowledge base. [/INST] Yes, absolutely. And we try to stay away from, um, projects, uh, that would not have that property. Um, so let me go back and talk about open psych for a second. So, I've had a lot of trouble expressing convincing other ai researchers how important it is to use an expressive representation language, like we do this higher order logic rather than just using some triple store knowledge, graph type representation. Um, and so as an attempt to show them why they needed something more, we said, oh, well, well represent this unimportant projection or shadow or subset of psych that just happens to be the simple binary relations, the relation, argument one, argument two, triples and so on. Um, and then you'll see how much more useful it is if you had the entire site system. So it's all well and good to have the taxonomic relations between terms like person and night and sleep in bed and house and eyes and so on. But think about how much more useful it would be if you also had all the rules of thumb about those things like people sleep at night, they sleep lying down, they sleep with their eyes closed, They usually sleep in beds in our country. Uh, they sleep for hours at a time. They can be woken up. They don't like being woken up and so on and so on. So it's that massive amount of knowledge, which is not part of open psych. And we thought that all the researchers would then immediately immediately say, oh my God, of course we need the other 90% that you're not giving us, let's partner and license psych so that we can use it in our research. But instead what people said is, oh, even the bit you've released is so much better than anything we had. We'll just make do with this. And so if you look, there are a lot of robotics companies today, for example, which use open psych as their fundamental ontology. Um, and in some sense, the whole world missed the point of open psych and we were doing it to show people why that's not really what they wanted. And too many people thought somehow that this was psych or that this was in fact good enough for them and they never even bothered coming, um coming to us to get access to the full psych, </s>
<s>[INST] that's the way to maximize. So like the selfishness is you're trying to maximize the wind, but the way to maximize the wind is to maximize the win win. [/INST] Yes, and and it turns out and Adam smith understood this a long time ago that if you focus on your own winning while respecting other people as human beings, then everybody wins. And the beauty of capitalism, if we go back to capitalism for a second, The beauty of capitalism is you cannot be successful in capitalism without producing values that other people appreciate and therefore willing to buy from you and they buy them. And this goes back to that question about the engineer and steve jobs, Why is an engineer working there? Because he's getting paid more than his time is worth to him. I know people don't like to think in those terms, but that's the reality. If his time is worth more to him than what he's getting paid, he would leave. So he's winning and his apple winning. Yes. Because they're getting more productivity from him. They're getting more from him than what he's actually producer. </s><s>[INST] It's tough because there's a human psychology and imperfect information. It just makes it a little messier than the clarity of thinking you have about this. It's just, you know, because for sure, but not everything in life is an economic transaction. It ultimately it's close. But even [/INST] if it's not an economic transaction, even if it's a if it's a it's a relationship transaction, when you get to a point with a friend, well, you're not gaining from the relationship friendship is going to be over. Not immediately because it takes time for these things to manifest itself and to really absorb into. But we change friendships, we change our love's right? We fall in and out of love. We fall out of love because we're not love. So let's let's go back to love it. Love is the most selfish of all emotions. Love is about what you do to me, right? So I love my wife because she makes me feel better about myself. So you know, the idea of selfless love is bizarre. So I man used to say before you say I love you, you have to say that I Mhm and you you have to know who you are and you have to appreciate yourself if you hate yourself, what does it mean to let somebody else? So my I love my wife because she makes me feel great about the world and she loves me for the same reason. And so I used to use this example, imagine you go up to your to be spouse the night before the wedding and you say, you know, I get nothing out of this relationship. I'm doing this purely as an act of noble self </s><s>[INST] sacrifice. [/INST] She would slap you as she should, right? So, you know, we know this intuitively that love is selfish, but we afraid to admit it to ourselves and why? Because the other side has convinced us that selfishness is associated with exploiting other people, selfishness means lying, cheating, stealing, walking and corpses backstabbing people. But is that ever in your self interest truly right? You know, I'll offer be in front of an audience to say, okay, how many people here have lied? I'm you know kidding, right? How many of you think that that if you did that consistently, that would make your life better. Nobody thinks that because everybody's experienced how should he lying? Not because of how it makes you feel out of a sense of guilt, existentially just a bad strategy, right? You get caught, you have to create other lies to cover up the previous lie. It screws up with your own psychology and your own cognition. You know, the mind, to some extent, like a computer right, is an integrating machine and a computer science. I understand there's a term called garbage in garbage out lying is garbage it. So it's not good strategy cheating, uh, screwing your customers in a business, not paying your suppliers as a businessman, not good business practices, not good practices for being alive. So Win Win is both moral and practical and the beauty of Fine man's philosophy. And I think this is really important is that the model is the practical and the practical is the mall and therefore if you are morrow, you will be happy. </s><s>[INST] Yeah, that's the that's why the application of the philosophy of objectivism is so easy to practice. So like they are to discuss or possible to discuss. That's why you [/INST] talked about a clear cut. I'm not ambiguous about </s><s>[INST] my view and that's fundamentally practical. I mean, that's the best of philosophies is practical. [/INST] It's in a sense teaching you how to live a good life. And it's teaching you how to live a good life, not just as you, but as a human being and therefore the principles that apply to you probably apply to me as well. And if we both share the same principles of how to live a good life, we're not going to be enemies. </s><s>[INST] You brought up anarchy earlier. Uh, it's an interesting question because you've kind of said politicians, I mean part of it is a little bit joking, but politicians are, you know, not good people. So, but we should have some, so you have an opposition to anarchism. [/INST] So the first of all, they weren't always not bad people. That is, I gave examples of people who engage in political life. I think we're good people basically. Um, and and but they think they get worse over time if the system is corrupt. And I think the system, unfortunately even the american system as good as it was, was founded on quicksand and have corruption built in. Um they didn't quite get it and and they needed an event to get it. So I'm not blaming them. I don't think they hope they show any blame. You needed a philosophy in order to completely fulfill the promise that is America. The promise that is the founding </s>
<s>[INST] That's a love has it. So at which point do the classical philosophers end at this point we're in the 21st century, what's what's the latest classical philosopher does this stretch through even as far as Nietzsche or is this what we're talking about plato and Aristotle? And [/INST] I think that nature is the classical equivalent of a ship poster. So it's very difficult to read. And yeah, but he's not so much trawling others, he's trolling himself because he was at odds with the world, largely his romantic relationships didn't work out, he got angry and he basically became a nihilist. And </s><s>[INST] isn't that uh is that a beautiful way to be as an intellectual is to constantly be trolling yourself to be in that conflict? In that [/INST] a lack of self awareness at some point, you have to understand the comedy of your own situation if you take yourself seriously uh and you are not functional, it ends in tragedy as it did for nature. </s><s>[INST] I think you think he took himself too seriously in that in that tension [/INST] and as you find the same thing in Hesse and so on this step involved in dramas classic at dollar sense where you basically feel misunderstood by the world and you don't understand that all the misunderstandings are the result of your own lack of self awareness because you think that you are a prototypical human and the others around you should behave the same way as you expect them based on your innate instincts. And it doesn't work out and you become a transcendentalist to deal with that. So it's very, very understandable and have great sympathies for this, to the degree that I can have sympathy for my own intellectual history. But uh out of </s><s>[INST] it was an intellectual, a life well lived, a journey while traveled is one where you don't take yourself seriously. [/INST] I think that you need a serious or not serious uh yourself because you need to become unimportant as a subject. That is, if you are a philosopher, belief is not a verb, uh you don't do this for the audience, You don't do it for yourself. You have to submit to the things that are possibly true and you have to follow wherever your career elites, but it's not about you. It has nothing to do with you. </s><s>[INST] So do you think uh then people like Ayn rand believed sort of an idea of there's an objective truth. So what's your sense in the philosophical, if you remove yourself that's objective from the picture, you think it's possible to actually discover ideas that are true or are we just in a measure of relative concepts? There, neither true nor false. It's just a giant mess. [/INST] You cannot define objective truth without understanding the nature of truth in the first place, or what does the brain mean by saying that discover something as truth. So, for instance, a model can be predictive or not predictive. Um then there can be a sense in which a mathematical statement can be true because it's defined as true under certain conditions. So it's basically a particular state that uh, variable can have an assembled game. And then you can have a correspondence between systems and talk about truth, which is again a type of model correspondence. And there also seems to be a particular kind of ground truth. So, for instance, you're confronted with the enormity of something existing at all. Right. It's stunning when you realize something exists rather than nothing. And this seems to be true, right? There is absolute truth in the fact that something seems to be happening. </s><s>[INST] Yeah, that's that to me is a showstopper. I can just think about that idea. I'd be amazed by that idea for the rest of my life and not go any further because I don't even know the answer to that. Why does anything exist at all? [/INST] The easiest answer is existence is the default. Right? So this is the lowest number of pits that you would need to encode this whose answer who brought? The simplest answer is that existence is the default. </s><s>[INST] What about non existence? I mean, that seems [/INST] non existence might not be a meaningful notion in this sense. So, in some sense, if everything that can exist exist for something to exist, it probably needs to be implemented all the only thing that can be implemented as finite automata. So maybe the whole of existence is the superposition of all finite automata and we are in some region of the fractal that has the properties that it can contain us. </s><s>[INST] What does it mean to be a superposition of fine adult spanish uh superposition of all. Like all possible rules. [/INST] Imagine that every automaton is basically an operator that acts on some substrate and as a without you get emergent patterns most of substrate. Um no idea to know. So it's based on substrate. It's some some something that can store information, </s><s>[INST] something that can store information. There's a time [/INST] to something that can hold state </s><s>[INST] still doesn't make sense to me. The why that exists at all. I could just sit there with a, with a beer or vodka and just enjoy the fact monitoring the Y [/INST] may not have a while, there might be the wrong direction to ask into this. So there could be no relation in the right direction without asking for a purpose or for a cost. It doesn't mean that everything has to have a purpose or cause. Right. </s><s>[INST] So we mentioned some philosophers in that early, just taking a brief step back into into that. [/INST] So we asked ourselves when the classical philosophy and I think for Germany largely ended with the first revolution. That's basically when was that? This was when we entered the monarchy and started a democracy. And at this point b basically came up with a new form of government that didn't have a good sense of this new organism that society wanted to be. And in a way that decapitated the universities. So the university spent on to modernism like a headless chicken. At the same time, democracy failed in Germany and we got fascism as a result and it burned down things in a similar way as stalinism burned down intellectual traditions in Russia and Germany. Both Germany's have not recovered from this Eastern Germany had this vulgar dialectic materialism in Western Germany didn't get much more edgy than Obama's. So in some sense, both countries lost their intellectual traditions and killing off and driving out the jews didn't help. Uh huh. </s>
<s>[INST] Yeah. There should be a humility with that. Like the, I mean, we should actually say that we like literally the [/INST] we lost you lost. It wasn't just, you know, um </s><s>[INST] the american military [/INST] lost. Yeah. And I feel I have very mixed feelings and you know, it's, I don't know a ton of veterans, but you know, I've mentioned, I've taught my share and um have a student now and you know, they are, they're suffering because they look at the sacrifices that they made that I didn't make. I mean, american society to make the sacrifices. I mean, men and women lost limbs, They lost eyes, they lost lives. You know, uh there's been this of course quiet epidemic of suicide among among veterans and I I've heard some stories, the fact that the state Department is seeing a similar surge of suicide because they see their adult life's work collapse. They've seen the relationships. I mean, they've seen they received phone calls in middle of night from people who they entrusted their lives, who they know we're gonna be targeted. Some have already been killed. Um, they've seen the, I mean, I think just I'd imagine just logically and professionally, what they believed in and what they, what I sacrificed for you have vanished. And I think that's a that's that's bad. I mean, historically thinking of some of the presents you're thinking, I mean, if you think of, you know, first of all, a human level, I feel horrible for those people who, you know, may not have agreed with everything they've done and their choices life. But I respect the fact that many good people went out of, you know, the best intentions as young people to do the right thing and make things right. And I respect that. And I've met enough to know that there were people who I saw the gray and complexity and that that's, you know, all you can hope for. Um, but we don't want a generation of disillusioned veterans. Um, you know, if you look at the other Postwar moments and this is kind of Postwar moment where, you know, I think we need a conversation with american veterans about, about what they've gone through and what they're feeling they have, they have skin in the game. You know, because they're personal connections and their and their histories are also going to be </s><s>[INST] future leaders. I mean, [/INST] uh veterans, people </s><s>[INST] who have served are often great men and women. That's that's true and mhm. You know, throughout history, whether your sacrifices served in fighting World War Two in fighting Vietnam, that's going to mold you in different ways. That's going to mold how you are as the leader that leads this country forward. And uh so you have to have an honest conversation about what was The role of the war in Afghanistan? The war in the Middle East, the war on terror in the history of America. If we just look at the full context at the end of this 21st century, how we're going to remember this and how that's going to result in our future interactions with small and large countries with china or some proxy war with china with Russia or some proxy war with Russia was the role of oil and natural resources and opium and all those kinds of things. What's the role of military power uh in the world? And now with Covid, you know, it's like uh it's almost like the because of the many failures of the U. S. Government and many leaders uh in science and politics to respond effectively and quickly to uh to Covid. We kind of forget that we fumbled this other thing too. And it's it's hard to know which is going to be more expensive, uh they seem to be symptoms of something of the same kind of source problem um of leadership of bureaucracy, of of the way information and intelligence flows throughout the U. S. Government, all those kinds of things and then hopefully motivates young leaders to fix things [/INST] definitely. I mean, if there's one theme that jumps out to me and think about this moment, I mean, if we recognize that we live in a kind of crisis of democracy um in the United States and in other countries that have long been part of the democratic traditions. If we see them being under assault from some quarters, I think military defeat is yet another addition to all the the aspects of this that you mentioned. I mean, the fact that military defeat is a giant match that you're throwing on this fire, potentially if we think of its legacies and other post war environments, when, you know, the veteran angle, you know, it was one when you have people who feel betrayed. I mean, they have been fodder for the far right and other settings. I mean, interwar europe is very much about mobilizing dissolution veterans, the name of right wing fascist politics. Um if one thing's too, at this moment Of really increasing xenophobia, you know, our immigration debate is now talking about whether or not Afghans should be permitted at all in the United States, you know, after 20 years and I think immediately the response in europe, which I followed to some extent, you know, focusing on Germany because it was really ramping up deportations of afghans leading up this collapse. And now they have been, you know, a lot of right wing center right politicians in Germany have been watching all this with an eye to and using it to their advantage for a domestic german audience to say, you know, in the context of the recent elections that we are the party who will defend you against these afghans are gonna be coming from this. So you know what I've tried to emphasize in talking to different groups about this moment is that it won't be confined to Afghanistan or even the region. I mean obviously malnutrition, hunger will send afghans to neighboring states, but where the european right is resurgent. This has been a gift right to say that the Africans are coming, they're brown skinned, their muslim, they're uneducated, they're gonna want your women um and they will take, you know, the odd sexual assault case or the odd whatever um dramatic act of violence that yeah, happens numerically in any population and they will magnify that to say that yeah, are far right group is going to save the nation. And sorry, that the main point I wanted to be in leadership was that I think the cereal, well there are many, many um carnal sins if you like. But if you go back to our analogy of all the exits, I mean what blocked some of those exits was um an absence of truth and transparency and the lying. And so I mean, that this is no secret one has followed this, but the we've allowed you think of the general mistrust of government, mistrust of of authoritative of authority across the board, professors of economists, of scientists, scientists, Doctors, doctors. Right? </s>
<s>[INST] and that's the excitement that you felt that from these simple things you can emerge when you add these level of abstractions on it, you can start getting all the beautiful things that we think about is cognition and so okay, so you have this conference, I forgot the name already but it's parallel and something associated with memory and so on. Very exciting, technical and exciting title. And you started talking about Dave Roma heart. So who is this person that was So you've spoken very highly of him, can you tell me about him his ideas, his mind, who he was as a human being, as a scientist. [/INST] So Dave came from a little tiny town in Western South Dakota and his mother was the librarian and his father was the editor of the newspaper. Um And I know one of his brothers pretty well. They grew up There were four brothers and they grew up together uh and their father encouraged them to compete with each other a </s><s>[INST] lot. [/INST] They competed in sports and they competed in mind games, you know, um I don't know, things like Sudoku and Chest and various things like that. And uh Dave was uh standout undergraduate. He went uh as at a younger age than most people do to college at the University of South Dakota and majored in mathematics. And I don't know how he got interested in psychology, but he applied to the mathematical psychology program at stanford and was accepted as a PhD student to study mathematical psychology at stanford. So mathematical psychology uh is the use of mathematics to model mental processes. </s><s>[INST] So something that I think these days might be called cognitive modelling that whole space. [/INST] Yeah, it's mathematical in the sense that um you say if this is true and that is true, then I can derive that this should follow. Okay. And so you say these are my stipulations about the fundamental principles and this is my prediction about behavior. And it's all done with equations. It's not done with the computer simulation. Right? So you you solve the equation and that tells you what probability that the subject will be correct on the seventh trial or the experiment is or something like that. Right? So it's a it's a it's a it's a use of mathematics to descriptively characteristic uh aspects of behavior and stanford at that time was the place where uh there were several really, really strong mathematical thinkers who were also connected with three or four others around the country who um you know, brought a lot of really exciting ideas onto the table and it was a very, very prestigious part of the field of psychology at that time. So Rummelhardt comes into this um he was a very strong student within that program. Uh and uh he got this Job at this brand new university in San Diego in 1967. He's one of the first assistant professors in the department of Psychology at UcsD. So I got there In 74 7 years later and wrong hard at that time, was still doing mathematical modeling. Um but he had gotten interested in cognition. He'd gotten interested in understanding and understanding, I think remains, you know, what does it mean to understand anyway, you know? Uh It's an interesting sort of curious, you know, like how would we know if we really understood something, but but he was interested in building machines that would, you know, here a couple of sentences and have an insight about what was going on. So, for example, one of his favorite things at that time was um marquis was sitting on the front step when she heard the familiar jingle of the good humor man. She remembered her birthday money and ran into the house, what is margie doing? Why? Well, there's a couple of ideas you could have, but The most natural one is that the good humor man brings ice cream, she likes ice cream, she she knows she needs money to buy ice cream, so she's going to run into the house and get her money so she can buy herself an ice cream. It's a huge amount of inference that has to happen to get those things to link up with each other. And and he was interested in how the hell that could happen, and he was trying to build um you know, good old fashioned ai style models of representation of language and and content of, you know, things like has money, </s><s>[INST] so, like, like formal logic and acknowledged basis, like that kind of So he was integrating that with his thinking about cognition, the mechanisms cognition, how can they, like, mechanistic lee be applied to build these knowledge, like to actually build something that looks like a web of knowledge and their buys from from there emerges something like understanding what the heck that is. [/INST] Yeah, he was grappling that this was something that they grappled with at the end of that book that I was describing explorations in cognition, but he was realizing that the paradigm of good old fashioned a I wasn't giving him the answers to these questions </s><s>[INST] and by the way that's called good old fashioned I know it was [/INST] well it was it was beginning to be called that </s><s>[INST] Because it was from the 60s yeah, [/INST] by by the late seventies, it was kind of old fashioned, it hadn't really panned out, you know, and people were beginning to recognize that, but and Rummelhardt was, you know, like yeah, he's part of the recognition that this wasn't all working anyway, so he um started thinking in terms of uh the idea that we needed systems that allowed us to integrate multiple simultaneous constraints in a way that would be mutually influencing each other. So um he wrote a paper that just really first time I read it, I said, oh well, you know, yeah, but is this important? But after a while it just got under my skin and it was called an interactive model of reading. And in this paper he laid out the idea that every aspect of are interpretation of what what's coming off the page. When we read at every level of analysis you can think of actually depends on all the other levels of analysis. So yeah, what are the actual pixels making up each letter? And what do those pixels signify about which letters they are and what are those letters? Tell us about what words are there? And one of those words tell us about what ideas the author is trying to convey. And so he had this model where, you know, we have these little tiny uh elements that represent each of the pixels of each of the letters and then other ones that represent the line segments in them and other ones that represent the letters and other ones that represent the words. And um at that time his idea was there's this set of experts, there's an expert about how to construct a line out of pixels. And another expert about how which sets of lines go together to make which letters and another one about which letters go together to make mitch words. And another one about what the meanings of the words are. And another one about how the meetings fit together and you know, things like that and all these experts are looking at this data and their their um updating hypotheses at other levels. So the word expert can tell the letter expert oh I think there should be a T there because I think there should be a word the here and the bottom up sort of featured two letter expert can say, I think there should be a T. There too and if they agree then you see a T. Right. And so there's a top down bottom up interactive process but it's going on at all layers simultaneously. So everything can filter all the way down from the top as well as all the way up from the bottom. And it's a completely interactive bidirectional parallel distributed process. </s>
<s>[INST] But there is that access of decency, which is really interesting because you kind of painted this picture of you and your friends arguing really harshly. But underlying that is a basic camaraderie, respect, there's all kinds of mechanisms we humans have constructed to communicate, like mutual respect, or maybe communicate [/INST] that you're here for the ideal lab version of this. Totally, you don't take it, you don't get personal, right? You're not getting personal, </s><s>[INST] you're not taking things personally. [/INST] People are respected in an ideal lab and ideas are disrespected. </s><s>[INST] And there's ways to signal that. So like with friends, you've already done the signaling, you've already established a relationship. The interesting thing is online, I think you have to do some of that work. I mean, to me, sort of steelmanning the other side, or no, having empathy and hearing out, being able to basically repeat the argument the other person is making before you and showing like respect to that argument. I could see how you could think that before you make a counter argument. There's just a bunch of ways to communicate that you're here not to do kind of, what is it, low rung, shit talking, mockery, derision, but are actually here ultimately to discover the truth and the space of ideas and the tension of those ideas. And I think it's, I think that's a skill that we're all learning as a civilization of how to do that kind of communication effectively. Because I think disagreement, as I'm learning on the internet, it's actually a really tricky skill. Like high effort, high decency disagreement. I gotta listen to, there's a really good debate podcast, Intelligence Squared. And they can go pretty hard in the paint. It's a classic idea lab. Exactly, but how do we map that to social media? When people will say, will say, well, Lex or anybody, you're not, you hate disagreement. You wanna censor disagreement. No, I love Intelligence Squared type of disagreement. That's fun. Classic idea lab, you wanna reduce assholes. And for me personally, I don't want to reduce assholes. I kind of like assholes, it's fun in many ways. But the problem is when the asshole shows up to the party, they make it less fun for the party that's there for the idea lab. And the other people, especially the quiet voices at the back of the room, they leave. [/INST] And so all you're left is with assholes. Well, political Twitter to me is one of those parties. It's a big party where a few assholes have really sent a lot of the quiet thinkers away. And so if you think about this graph again, a place like Twitter, a great way to get followers is to be an asshole with a certain, pumping a certain ideology. You'll get a huge amount of followers. And for those followers, and the followers you're gonna get, the people who like you are probably going to be people who are really thinking with their primitive mind because they're seeing you're being an asshole, but because you agree with them, they love you. And they think they don't see any problem </s><s>[INST] with how you're being. Yeah, they don't see the asshole. [/INST] This is a fascinating thing because of... Because look at the thing on the right. Agreement and decency are the same. So if you're in that mindset, the bigger the asshole, the better. If you're agreeing with me, you're my man, I love what you're saying. Yes, show them, right? And the algorithm helps those people. Those people do great on the algorithm. </s><s>[INST] There's a fascinating dynamic that happens because I have currently hired somebody that looks at my social media and they block people because the assholes will roll in. They're not actually there to have an interesting disagreement, which I love. They're there to do kind of mockery. And then when they get blocked, they then celebrate that to their echo chamber, [/INST] like, look at this, I got them, or whatever they do. Or they'll say some annoying thing like, oh, so he talks about, he likes, if I'd done this, they'll say, oh, he says he likes idea labs, but he actually wants to create an echo chamber. I'm like, nope, you're an asshole. I'm not, look at the other 50 people on this thread that disagreed with me respectfully. They're not blocked. Yep, exactly. And so they see it as some kind of hypocrisy because, again, they only see the thing on the right. And they're not understanding that there's two axes, or that I see it as two axes. And so you seem petty in that moment, but it's like, no, no, no, this is very specific what I'm doing. </s><s>[INST] You're actually killing the conversation. You're not blocking it. And generally, I give all those folks a pass and just send them love telepathically, but yes, getting rid of assholes in the conversation [/INST] is the way you allow for the disagreement. You do a lot of, I think, when primitive-mindedness comes at you, at least on Twitter, I don't know what you're feeling internally in that moment, but you do a lot of, I'm gonna meet that with my higher mind. And you come out and you'll be like, thanks for all the criticism. I love you. And that's actually an amazing response because what it does is that it unriles up that person's primitive mind and actually wakes up their higher mind who says, oh, okay, this guy's not so bad. And suddenly, civility comes back. </s><s>[INST] So it's a very powerful and very powerful. Hopefully long-term, but the thing is, they do seem to drive away high-quality disagreement because it takes so much effort [/INST] to disagree in a high-quality way. I've noticed this on my blog. One of the things I pride myself on is my comment section is awesome. Everyone's being respectful. No one's afraid to disagree with me and say, tear my post apart, but in a totally respectful way where the underlying thing is like, I'm here cause I like this guy in his writing and people disagree with each other and they get in these long interviews and it's interesting and I read it and I'm learning. And then a couple posts, especially the ones I've written about politics, it seems like any other comment section, people are being nasty to me, they're being nasty to each other. And then I looked down one of them and I realized like almost all of this is the work of like three people. That's who you need to block. Those people need to be blocked. You're not being thin skinned. You're not being petty doing it. You're actually protecting an idea lab, because what really aggressive people like that do is they'll turn it into their own echo chamber, because now everyone is scared to kinda disagree with them, just so it's unpleasant, and so people who'll chime in or the people who will agree </s>
<s>[INST] I'm using my gut instinct. Usually when somebody feels strongly about another person in that way. It's not coming from a place of data and reason, it's coming from a place of emotion. It's coming from a place of resentment and garage and all that kind of stuff. But there's emotions deep in there, so the gachu is hiding, the gachu is the surface of an iceberg and there's a deep ocean underneath [/INST] that you yourself have not explored. </s><s>[INST] And love is actually a doorway, the young love is a doorway for you to explore [/INST] the depths of the- Get into that ocean, find my fish, my pre-vol form. I understand why you think the way you do, and you should, you shouldn't believe me, And I understand that, because if somebody told me the same thing, I'd think, you'll probably just really don't like this person for a reason or two. I understand what you think that way, okay? The reality is though, for any political person that I disagree with, I can give them a fair shake. It's one of the few things I think I do exceedingly well on my stream. Even with Hassan, there's been drama that he's been involved in, and when I'm involved in drama, he'll always throw me on the bus, but when he's involved in stuff, I'll always be like, oh, I think Hassan was right here. Or, I think that he meant this. There was a thing that came up once where, on livestream failed, because he referred to somebody, he used the expression shit-skin to refer to somebody's the way they looked. And I have only ever heard that in the context of 4 Chant people talking about Indians or black people, it's a racial thing. But I could tell the context and everything that he was saying, he was insulting some guy, I think it was called Incel Virgen. He was going for acne skin. I think that's what he meant when he said it. And there are a whole bunch of people that were insulting, he was like, oh my god, did he say racist term. And I was like, no, I don't think he was racist. I think he was just reaching for words and that's what came out. </s><s>[INST] But didn't you criticize him for something? I was trying to like Google, why the hell are you guys split out. Cause I thought your friends should be like... Is that why... so I feel like you criticized him over something... okay, this is very vague memory but you criticized him over something and I felt that criticism was in charitable. Was it Pete Buttigieges' stuff? Yeah. Pete Buttigieges. [/INST] Yes, yes, yes, yes, in this Kamala Harris video, but go ahead, we're here, thank you so much. Yeah, so I've said this a million times, but there's no amount of context or no amount of nuances is ever acceptable to people. I don't think Hassan is homophobic, but I think the comments made about Pete Buttigieg were really homophobic. That's what he said, right. Yeah, and there were a lot of people making a lot of comments that made me really uncomfortable </s><s>[INST] about Pete Buttigieg that was insane to me, yeah. [/INST] Spurred by the comments of Hassan? No, but it was an environment of progressives all the progressives were attacking Pete, and I felt like his gayness became the subject of the attack. Yeah, but why throw Hassan under the bus for that? Because he was jumping along </s><s>[INST] with all of those types of insults. [/INST] You don't think you've done the same kind of stuff? If I do, call me out on it, </s><s>[INST] and I'll try with you, I shouldn't have done it. [/INST] That's what our word was about, but that's all for that. </s><s>[INST] That's a good call-out, yeah, yeah. No, but your friend, [/INST] you should privately tell him, right? Well, no, by then we were sworn enemies, so. So that wasn't the reason you- </s><s>[INST] No, no, no, it was over a Kamala Harris video. Worn enemies, my God. [/INST] He hates me, what am I, he hates me. What am I, listen, for all of these people, I will accept them back into my life, if they ever wanna come back in at any point in time, but usually they're the ones that- If they correct themselves, right? If they- No, I'm not expecting anybody to- So here's the deal with Vash and Hassan. These are like the three, we're the three guys online. None of us will talk to each other. Hassan because he won't give clout to anybody, and Vash because he thinks I'm bad faith. And then neither of them will talk to me </s><s>[INST] because they both hate me. You guys should go on a camping trip together. It's like broke back modern, but three-way, and just like rejoin, refine- Yeah, that could be a thing. Refine the vision for each other. Honestly, just from the internet perspective, for me as a, just stepping into this world, there's some aspect to which you have a responsibility. I hate that word. You have an opportunity- Good word, don't run from it. I wish you guys would kind of be the beacon of like, forgiveness and friendship and like camaraderie and that. [/INST] Yeah, I agree, word, don't run from it. Yeah, I agree. And even if we disagree, </s><s>[INST] it would be really good content for us to argue with. Yeah, shit talk, like friends shit talk. Versus not, like the fact that you guys don't talk to each other. Like I would love for you to shit talk publicly with the camaraderie always there. Like there's love in the beginning, love in the end, but you beat the shit out of each other in the middle. And that's what livestream means for, the political discourse. That's great political discourse. Versus I think what underlies it, some jealousy and so on. This you get this many fall- [/INST] I just want to make sure you're clear to your- </s>
<s>[INST] looking forward from a perspective of leadership. How do we avoid these kinds of mistakes? So obviously some interest some aspects of human nature led to this war. How do we resist that in the future? [/INST] Hang us beyond my moral and intellectual capacity to say this. I mean looking at again looking at it from my home ground is the university and I think of the the intellectual um yeah ways of ways of thinking that that students should develop themselves as citizens, right? Maybe that's where to start is like historical thinking. I mean these are all and I try to tell people, you know if you want to do robotics computer science you'd be a doctor whatever you </s><s>[INST] should study history. [/INST] Yeah. I mean you don't have a story like me and you know my job isn't perfect. My profession is deeply flawed, right? But as I get older I'm like there are fewer and fewer historians actually like you wanna hang out with and stuff. So it's like I'm not offering myself as like a model for anything but you know whether you're a you carry the mail or you're a brain surgeon whatever. I mean I think it's not it's it's a way of civic engagement in the way of like you know ethical thing in the world that we need to familiarize also because if you're american or if you're from a rich country, you know, you need to be aware of your effect on a, on an interactive world. You can't, you can't say anymore that you don't know or care what's happening in Afghanistan or really circle the globe and point to a place. I mean, we're all connected and we're all, we have ethical obligations. Um, that's one place. But I'll just say this though, and this is a lot for a self critique. And that is um some of my teaching and like the theme of my research about empire, how big states work, not only on big territories like the Russian empire and soviet union, stop it the way in which power often projected beyond those boundaries, in ways that we don't see. So this is where things like neoliberalism or just, you know, you want to take capitalism or just things that, you know, the idea of humanity or of liberalism or of humanitarianism, ideas that move beyond state boundaries are all things that we think about as affecting power in some ways that that often harm people, right? So I think part of I've seen my jobs as far as I think about, you know, building upon the work of my people in grad school and you know, scholars have affected me. I mean, you know, we're all concerned with how power works and its effects and trying to be attuned to understanding things that aren't visible, right, that we should be thinking about, that should be known to us. And the scholars, we can hopefully play some useful role in showing effects that aren't, you know, obvious initially. Um so empire is a framework to think about this. And so you think about invading foreign countries, obviously, if you're a scholar of empire, you've seen what that looks like and that's terrific, right. You think you look at things like racism as one of the ideological pillars of empire, You know, that's terrific, must be critiqued. It must be we must be educated against some of the gender exploitation of empire is also something to highlight to rectify and so on. Um you know, to be moral beings. When you think about past inequality and the legacies of legacies of violence and destruction that live on. I mean, living in America's, I mean, look at, you know, we're all on stolen land, we're all in the sense living with the fruits of genocide and slavery and all those things are hard to come to terms with right? But the last few months in Afghanistan and thinking about empire, I think maybe more humble when I read people who say to to put it simply have taken some joy in this moment saying like, well the americans got kicked out of Afghanistan. You know, if you're against empire, this is a good thing, this is a kind of victory of of anti colonial. </s><s>[INST] You can see from the perspective of Afghanistan that America is not some kind of place that has an ideal of freedom and all the kind of things that we american tell ourselves. But it's more America has the ideal of empire, that there's one place that has the truth and everybody else must follow this truth. And so from a perspective, Afghanistan, it could be a victory against this idea of centralized truth of empire. That's another way to tell this story. And then in that sense, it's a victory. And in that sense also, I mean, you push back against this somewhat this idea of Afghanistan as the graveyard of empires [/INST] and also this, that's it, you know, I mean, it's I mean, I'm a critic of empire. I mean, you know, colonialism is a a political phenomenon that stays with us and I think, you know, we need scholars to point the way in which is still works and still does harm. Um but it's part of being an empire that you can just get up and leave a place right, that you can free markets politics on one day and then because it fails to advance your agenda at one moment, you simply Walk away. I mean, you know, we can point to other moments, I mean 1947 on the subcontinent you know, the way that the british withdrew um played a significant role in mass violence. You know that the company partition, it wasn't all the actions of the british that you know, dictated that right. There were lots of actors who chose to pick up, you know, the knife to kill the neighbor and so on. I mean there's lots of agency in that moment as there is now in what's happening in Afghanistan. But I think the, the capriciousness, I mean the, the ability to act as if you're, you're your personal decisions about people's lives, you know, or something that can be made, you know in secret, um that can be made willy nilly. They really are beyond the accountability. You know, of, of those who are actually going to live with the consequences of shifting the cards in a deck in a way that decides who rules and who doesn't. </s>
<s>[INST] This has a large number of obvious benefits. Certainly it allows you to access international versions of streaming websites like the japanese netflix or the U K. Who Express VPN works on any device you can imagine. I used it on Lenox shoutout to bond to windows android but is available everywhere else too. Once again get it at Express VPN dot com slash lex pod to get a discount and to support this podcast. And now here's my conversation with Harry Cliff, [/INST] I thought </s><s>[INST] it was probably one of the coolest things that human beings have ever created. The large Hadron collider LHC, what is it? How does it work? [/INST] Okay, so it's essentially this gigantic 27 km circumference particle accelerators, this big ring buried 100m underneath the surface in the countryside just outside Geneva in Switzerland. And really what it's for ultimately is to try to understand what are the basic building blocks of the universe. So you can think of it in a way as like a gigantic microscope. And the analogy is actually fairly precise, so </s><s>[INST] gigantic microscope [/INST] effectively, except it's a microscope that looks at the structure of the vacuum </s><s>[INST] in order for this kind of thing to study particles uh which are microscopic entities. It has to be huge, gigantic microphone. So what do you mean by studying vacuum? [/INST] Okay, so I mean the particle physics as a, as a field is kind of badly named in a way because particles are not the fundamental ingredients of the universe, They're not fundamental at all. So the things that we believe are the real building blocks of the universe are objects, invisible fluid like objects called quantum fields. So these are fields like, like the magnetic field around a magnet that exist everywhere in space. They're always there. In fact, actually, it's funny that we're in the Royal Institution because this is where the idea of the field was effectively invented by Michael Faraday doing experiments with magnets and coils of wire. So he noticed that, you know, if he was very famous experiment that he did where he got a magnet and put it on top of it, a piece of paper and then sprinkled iron filings and he found the iron filings arrange themselves into these kind of loops of which was actually mapping out the invisible influence of this magnetic field, which is the thing, You know, we've all experienced, we all felt held a magnet and or two poles of magnet push them together and felt this thing was forced pushing back. So these are real physical objects. And the way we think of particles in modern physics is that they are essentially little vibrations, little ripples in these otherwise invisible fields that are everywhere, they fill the whole universe. </s><s>[INST] You know, I don't apologize perhaps for the ridiculous question. Are you comfortable with the idea of the fundamental nature of our reality being fields? Because to me, particles, you know, a bunch of different building blocks makes more sense, sort of intellectually sort of visually like it seems to uh I seem to be able to visualize that kind of idea easier. [/INST] Are you </s><s>[INST] comfortable psychologically with the idea that the basic building block is not a block but a field? [/INST] I think it's um I think it's quite a magical idea. I find it quite appealing and it's it's well it comes from a misunderstanding of what particles are. So like when you, when we do science at school and we draw a picture of an atom, you draw like, you know, nucleus with some protons and neutrons, these little spheres in the middle and then you have some electrons that are like little flies flying around the atom. And that is completely misleading picture of what an atom is like. It's nothing like that. The electron is not like a little planet orbiting the atom. Um it's this spread out wiggly, wobbly wave like thing and we know we've known that since, you know, the early 20th century, thanks to quantum mechanics. So when we we carry on using this word particle because sometimes we do experiments particles do behave like their little marbles or little bullets, you know, so the lhc when we collide particles together, you'll get, you know, you get like hundreds of particles or flying out through the detector and they all take a trajectory and you can see from the detector where they've gone and they look like they're little bullets. So they behave that way. Um, you know, a lot of the time. But when you really study them carefully, you'll see that they are not little spheres. They are these ethereal disturbances in these underlying fields. So this is this really how we think nature is, which is surprising, but also I think kind of magic. So we are our bodies are basically made up of like little knots of energy in these invisible objects that are all around us. </s><s>[INST] And uh what is the story of the vacuum when it comes to? Let's see. So why did you mention the word vacuum? [/INST] Okay, so if we just if we go back to like the physics, we do know. So atoms are made of electrons which were discovered 100 or so years ago. And then in the nucleus of the atom you have two other types of particles, there's an up something called an up quark and a down quark. And those three particles make up every atom in the universe. So we think of these as ripples in fields. So there is something called the electron field. And every electron in the universe is a ripple moving about in this electron field. The electron field is all around us. We can't see it. But every electron in our body is a little ripple in this thing. That's there all the time. And the quark fields the same. So there's an up quark field and an up quark is a little ripple. The up quark field and the down quark is a little ripple in something else called the down quark field. So these fields are always there now. There are potentially we know about a certain number of fields in what we call the standard model of particle physics. And the most recent one we discovered was the Higgs field. And the way we discovered the Higgs field was to make a little ripple in it. So what the LhC did, it fired two protons into each other. Very, very hard. With enough energy that you could create a disturbance in this Higgs field. And that's what shows up is what we call the Higgs bozon. So there's particle that everyone's going on about eight or so years ago is proof really, the particle in itself is, I mean, it's interesting, but the thing is really interesting is the field because it's the the Higgs field that we believe is the reason that electrons and quarks have mass. And it's that invisible field that's always there, that gives mass to the particles the Higgs bos on is just our way of checking it's there basically. </s>
<s>[INST] I say it even more emphatically now. Still, it is one of the most powerful words in the English language. And there's a kind of responsibility that we as humans should have with words, with statements. That word, if not used skillfully, if not used competently, even when just read from a legal transcript, [/INST] can do more harm than good. Yeah, I agree with what you say. Yes, words are powerful. Words do matter. And so I am certainly not suggesting that people be lax. I'm not suggesting that people be irresponsible. It's precisely because words matter, however, that we need to be willing to face words and grapple with words and talk about words and talk about the history of words, precisely because words matter. And among other things, it seems to me, it's important to understand that words can mean different things in different contexts. It's not the case that a word means the same thing in every context, the word discriminating. Sometimes it's a very bad thing. That person discriminates. And when, again, intonation of voice means something. If I say that person discriminates, and I'm obviously being disapproving, implicitly what I'm saying is that person distinguishes between things on an unjustifiable basis. And that's a bad thing. On the other hand, that person has discriminating taste. Oh, that means something very different. That means that the person differentiates in a way that shows that they understand the difference between excellent, good, and not so good. And we think that that's a good thing. So words can mean different things in different contexts. It seems to me that that's something that actually we ought to recognize and talk about. </s><s>[INST] Well, some words enter this territory of being a slur. And it seems like when they cross the line into being a slur, there's the number of contexts in which it's okay to mention it exponentially decreases. Right? [/INST] Uh, no, no, I'm gonna resist that a little bit because the whole idea of slurs, slurs change. Yankee was a slur. Yankee was a slur in 18th century United States. Slur today, New York Yankees, I'm a Yankee fan. I'm a Yankee, Queer, queer, and this is in my lifetime. There was a time you queer and people would really run away from it and that was a bad thing. And then, thank goodness, I'm a queer fan. Goodness, gay liberation movement, gay liberation movement, basically, we're not gonna run away from this. We're gonna grab this quote slur and we're going to affix it to ourselves. And we are going to repurpose it. Now, the word queer is again, you know, can it be a slur? Yeah, it can be a slur, doesn't have to be. And it seems to me that it's important for people to know about how a word, a symbol, in some context can be a slur, in some context, doesn't have to be. So the whole idea of what's a slur, </s><s>[INST] that's a complicated idea in and of itself. It's very complicated. It's, if I may say, almost fascinating how language evolves. But if we were to kind of have a minute by minute evaluation of the most powerful, intensely slur-like words in the world, I think the N word with a hard R at the end, which is the title of your book, [/INST] is number one on that list. Well, I probably so. And of course, that's one of the reasons </s><s>[INST] why I wrote a little book about it. Yeah, but it hasn't, even since you wrote a little book about it, it seems like it's maintained its number one status. You mentioned queer. Mm-hmm. Maybe queer was in the top 20, I don't know, for a while, and now it's sliding into the top 1,000, [/INST] and the N word is at the top. You're absolutely right. The origins of this book, I clearly remember, I was at my office and I was thinking about lecture topics. And I get invited to give lectures from time to time. And I was thinking, well, what might make for an interesting lecture? And all of a sudden, the word nigger popped into my mind. Now, this is a word, I've grown up with this word. I mean, there's never been a time in my life when, at least in my conscious life, in which this word's been absent. I mean, in my household, for instance, in my household, my parents are black people, my parents were refugees from the Jim Crow South. I was born in the Deep South, South Carolina. In my household, I heard the word nigger used in every possible way. I heard it used as a slur. I also heard it used with respect to people who were praised, you know? My father, I clearly remember my father, whom I revere. That's the smartest nigga in the world. That's the bravest nigga in the world. That's the baddest nigga I know. He wasn't putting people down. This is the way he talked. And I grew up hearing this word in various ways. And so I was thinking to myself, God, where did this word come from? And one of the first things I did, I clearly remember just jumping up out of my seat, running up to the library, Oxford English Dictionary. When did this word first appear in English? Was the history of the word. And then what really sort of grabbed my attention is I went, I get my computer going, and I asked the computer system, give me every case, every federal court case in which this word appears, thousands of cases. And then I said, oh my goodness, this is really, and you know, this is really interesting. And then I started just cataloging all the different cases. There came a point, I'd say probably about a month into this, I compared the usage, I compared the number of times a nigger came up with other sorts of slurs. So for instance, kike, K-I-K-E, long time, derogatory word for Jews. How many times has this word come up? There was a time in which the word appeared, but nothing like the infamous N word, nothing. What about wetback? What about, and then I just, let me just take a look at all the other slurs. Nothing came close, not even remotely close to nigger. And I think it has something to do with, I think it has something to do with the uniqueness of the color line, particularly as it pertains to African Americans. I think that the fact that nigger sort of occupies such a unique status among slurs, I think that's a reflection of the unique stigma </s>
<s>[INST] I've seen you break out of that a few times, I've seen you to be successful. That uh I forgot to guess. But she was dressed with um you were at the end of the episode, you had an argument about Brett I forgot this color Yeah, the [/INST] color, the philosophers at the University of Chicago. </s><s>[INST] Yeah, you've continuously broken out of her. You guys went, you know, I didn't seem pretty genuine. [/INST] I like </s><s>[INST] her. I'm [/INST] completely ethically opposed to what she's ethically </s><s>[INST] for. She was great and she wasn't like that. You're both going [/INST] hard to grown up. Yeah, because I care about her, So that was awesome. </s><s>[INST] Yeah, but you're saying that some people are difficult to break up? Well, [/INST] it's just that, you know, she was bringing the courage of her convictions. She was sort of defending the system. And I thought, wow, that's a pretty indefensible system. That's </s><s>[INST] great though, she's doing that, isn't it? I mean, it made for an awesome, [/INST] it's very informative for the </s><s>[INST] world. You just hated. [/INST] I just can't stand the idea that somebody says, well we don't care who gets paid or who gets the credit as long as we get the goodies, because that seems like insane. </s><s>[INST] Have you ever been afraid bleeding into a conversation? Uh [/INST] Garry Kasparov. Really? </s><s>[INST] Uh by the way, I mean uh no, I'm just a fan taking requests, but [/INST] I started I started the beginning in Russian and in fact I used one word incorrectly. It was terrible. You </s><s>[INST] know, it was pretty good. It's pretty good Russian, what was terrible and I think he complimented to you, right? No, did he complimented use let me do you compliment you on your Russian? [/INST] He said almost perfect Russian. </s><s>[INST] Yeah. Like he was full of sh it, that was not great Russian, but that was not great Russian. That was that was hard. You tried hard, which is what matters. That is so insulting. I hope so, but I do hope you continue. It felt like, I don't know how long it went, it might have been like a two hour conversation, but it felt I hope it continues. Like, I feel like you have many conversations with Gary. Yeah, I I would love to hear, there's certain conversation, I would just love to hear a lot of, much, much longer. [/INST] He's coming from a very it's this issue about needing to overpower people in a very dangerous world and so Gary has that need um </s><s>[INST] Yeah, he wasn't, he was interrupting you. It's an interesting dynamic. It was, it was an interesting dynamic to Weinstein's going into one, I mean, two powerhouse egos, brilliant. You definitely don't say egos, [/INST] minds, </s><s>[INST] my spirits, you don't have an ego, you're the most humble person I know. Is that true? No, that's a complete lie. Do you think about your own mortality? Death? Sure. Are you afraid of death? [/INST] I released the theory during something that can kill older people. Sure, </s><s>[INST] I was there, of course, a little bit of a parallel there. Of [/INST] course, of course, I don't want to die with me. </s><s>[INST] What do you hope your legacy is? [/INST] Oh, I hope my legacy is accurate. Okay, I'd like to write on my accomplishments rather than how my community decided to dig me while I was alive, that would be </s><s>[INST] great. What about if it was significantly exaggerated, [/INST] they don't want it. </s><s>[INST] You wanted to be accurate. Uh [/INST] I've got some pretty terrific stuff and whether it works out or doesn't that I would like it to reflect what I actually was, I'll settle for character. </s><s>[INST] What would you say? What is the greatest element of uh eric weinstein accomplishment in life in terms of being accurate? Like what, what are you most proud of [/INST] trying the idea that we were stalled out in the hardest field at the most difficult juncture and then I didn't listen to that voice ever that said, stop, you're hurting yourself, you're hurting your family, you're hurting everybody, You're embarrassing yourself, You're screwing up, you can't do this. You're a failure. You're a fraud. Turn back. Save yourself like that voice. I didn't ultimately listen to it and it was going for 35, years. Very hard </s><s>[INST] and I hope you never listen to that voice. That's why you're an inspiration. Thank you. [/INST] I appreciate that. You're </s><s>[INST] the I'm just infinitely honored that you would spend time with me. You've been a mentor to me almost a friend. I can't imagine a better person to talk to him as well. So thank you so much for talking to me. I [/INST] can't wait till we do it again, lex. Thanks for sticking with me and thanks for being the most singular guy in the podcasting space in terms of all of my interviews, I would say that the last one I did with you, many people feel was my best And it was a non conventional one. so whatever it is that you're bringing to the game, I think everyone is noticing and keep at it. Thank you. </s><s>[INST] Thanks for listening to this conversation with eric Weinstein and thank you to our presenting sponsor cash app. Please consider supporting the podcast by downloading cash app and using Code Lex podcast. If you enjoy this podcast, subscribe on youtube, review it with five stars on Apple podcast, supporter on patreon or simply connect with me on twitter Elex Friedman and now let me leave you with some words of wisdom from eric Weinstein's first appearance on this podcast. Everything is great about war except all the destruction. Thank you for listening and hope to see you next time. [/INST] Yeah. </s>
<s>[INST] where it's just having money doesn't, you know? Well, one interesting question I have for you psychologically. So because you have become wealthy and because you give, like part of your work is giving away a lot of money, do you find it hard to find people you can trust? It's a good question. Do people see you basically as a source of money? [/INST] As opposed to another human being. A good question. As opposed to another human being? It's weird because you'd think yes, but I feel like I also know the right places to look. But yeah, if I just walked into Target and tried to make friends with 10 random people, of course. </s><s>[INST] You can kind of sense. Oh yeah, you can sense the right thing in their heart. [/INST] So quickly, oh yeah, you could sense the right thing in their heart. So quickly, wait, yeah. Yeah. It's so obvious. I don't even want to go into the descriptions, but honestly, a lot of my friends, like Chandler, I played Little League with him, and Tyler, the guy, I mean, I went to school with him, Chris, he was my first subscriber. Carl was here after we got big, but whatever, he's friends with the boys, and it is a lot of my closer friends, even like my YouTube friends, I knew before I was big. So maybe there is some merit to that, maybe it is, I don't know, I've never really put too much thought into him, maybe there's a reason I hang around a lot of these people I knew before I got big because it's much easier. </s><s>[INST] And they help you keep your radar sharp of who can and can't be trusted, because you know you can trust them. It's difficult when you become richer and richer [/INST] and more powerful. Well, one thing you'll also find when you get richer, not even richer, but more famous, one thing I thought is as I climbed this ladder of YouTube and got bigger, I thought there would be tons of people like me, people that take the kamikaze approach and building a business, you just throw all your money in it, you throw all your time, you throw all your energy, you throw everything, you're just like fuck it, if it's this or I'm dead. And I thought there'd be hundreds of me. And there is like maybe one or two, and I talk to those motherfuckers every single day, sick and tired of talking to them, but I love them. But it's just so interesting, because every level I got up I'd get a million subscribers, I'd be like alright, where's all these guys with a million subscribers that are fucking psychopaths? </s><s>[INST] You know, you know, they're like- Yeah, people become like conservative as they get, [/INST] they get more and more- Especially as they get bigger, yeah. And you know, 20 million subscribers, 30, it's like every step of the way, it's like, I just got more and more lonely to be honest. So if you, you know, it sounds cliche and you hear that kind of shit in movies and you're like, oh, that's not how it works, but it is like there's just not many people that just want to give up everything, go all in and obsess over making the greatest goddamn videos every single day of their life, like, </s><s>[INST] they're really hard to find. And be able to sacrifice everything for that video. Yeah. [/INST] Like basically put all the money right back in. Yeah, or the people doing it, they're on just a small scale and if I talk to them, it's just 99.9% of the time </s><s>[INST] I'm teaching them things and it's like- So it's lonely because there's not too many people, [/INST] especially in the creative space, they're as crazy as you. Yeah, it is, 100%. It's so, it's not what I was expecting. </s><s>[INST] I was expecting there'd be a lot of people like me, but- Well, I guess the guy who talked to you on Musk is a bit like you in that sense. Yeah, just in a different domain, yeah. Exactly. Just willingness to put it all back in, right? [/INST] Yeah, just in a different domain, yeah. Exactly. And that's why I've found right now, a lot of the people I relate to don't even make YouTube videos. Like, I'm veering more and more away from fellow content creators and more to just, I'm just looking for those other people who just share a little bit of it so I don't feel so fucking crazy all the time. Like, you know what I mean? It's like, people I feel normal around, they tend to just be doing the randomest things, </s><s>[INST] but, you know, loving it. Well, I think that's really inspiring. It's like the Bukowski line, find what you love and let it kill you is really put everything, put everything into the thing you love. And that's like the way to really create special stuff, but it's also the way to- Yeah, it's- [/INST] Live out your life, most of all- Yeah, it's- Live out your life, most of all. Yeah, it's, you have to be careful giving this advice, because they're like, they're like body builders. You'll be like, just go to the gym. You gotta be disciplined, I'm disciplined, go to gym, but I would argue for those people it's like, it's not even disciplined, they just enjoy weightlifting. Because there are people who are jacked but they don't make much money or run a business. If they were that disciplined they would be hitting every area of their life, they just really like business and there's people like me who just to an extreme level, love building companies. It's not even disciplined for me, it's just in my blood, it's what I wake up, I don't think about it, I don't push myself, I don't need to watch a fucking motivational video to go work. It's programmed in me at this point and I couldn't imagine a world where I don't wake up and do it every day But I think that a little bit of it is genetics and just how you're hardwired Not that it can't be trained or taught and not that you know And obviously the friend group you're in influences these things and over time I think can change it but Someone's just not gonna be able to flip a switch and then just start doing a kamikaze approach to building a business Just like a lot of people try to flip a switch and start bodybuilding and quit majority of the time </s>
<s>[INST] So you have… So what was the temperature of the plasma? About 10,000 degrees. You can stick your hand in? [/INST] About 10,000. Well, you can't stick your hand into it, but there's a glass tube, you can basically see this. Yeah. And you can put your hand on the glass tube because it's, what color is it purple? It's purple. Yeah. It is kind of beautiful. Plasmas are actually quite astonishing sometimes in their beauty. Actually, one of the most amazing forms of plasma is lightning, by the way, which is instantaneous form of plasma that exists on Earth, but immediately goes away because everything else around it is at room temperature. That's fascinating. Yeah. So there's different requirements in this. So making a plasma takes about this, but at 10,000 degrees, even at a million degrees, there's almost no probability of the fusion reactions occurring. And this is because while the charged particles can hit into each other, if you go back to the very beginning of this, remember I said, oh, these charged particles have to get to within distances which are like this size of a nucleus because of the strong nuclear force. Well, unfortunately, as the particles get closer, the repulsion that comes from the charge, the Coulomb force, increases like the inverse </s><s>[INST] distance squared. Oh no. So as they get closer, they're pushing harder and harder apart. What's [/INST] the color is it purple? Yeah. So then it gets a little bit more exotic, which maybe you'll like though, that it turns out that people understood this at the beginning of the age after Rutherford discovered the nucleus. It's like, oh yeah, it's like, how is this going to work, right? Because how do you get anything within these distances? It's going to require extraordinary energy. And it does. And in fact, when you look at those energies, they're very, very high. But it turns out quantum physics comes to the rescue because the particles aren't actually just particles. They're also waves. This is the point of quantum, right? You can treat them both as waves and as particles. And it turns out if they get in close enough proximity to each other, then the particle pops through basically this energy barrier through an effect called quantum tunneling, which is really just the transposition of the fact that it's a wave so that it has a finite probability of this. By the way, you talk about, do you have a hard time conceptualizing this? This is one of them. Quantum tunneling is one of them. This is like throwing a ping pong ball at a piece of paper, and then every 100 of them just magically show up on the other side of the paper without seemingly breaking the paper, </s><s>[INST] I mean, to use a physical analogy. Quantum tunneling is one of them. And that phenomena is important, is critical for the function of nuclear fusion. [/INST] Yes, for all kinds of fusion. So this is the reason why stars can work as well too. Like the stars would have to be much, much hotter actually to be able to, in fact, it's not clear that they would actually ignite, in fact, without this effect. So we get to that. So this is why there's another requirement. So you must make a plasma, but you also must get it very hot in order for the reactions to have a significant probability </s><s>[INST] to actually fuse. And it actually falls effectively almost to zero for lower temperatures as well too. So there's some nice equation that gets you to 50 million degrees. Or like you said, practically speaking, a hundred million. [/INST] Yeah, it's a really simple equation. It's the ideal gas law basically, almost. So in the end, you've got a certain number of particles, of these fusion particles in the plasma state, they're in the plasma state. There's a certain number of particles. And if the confinement is perfect, if you put in a certain content of energy, then basically, eventually they just, they come up in a temperature and they become, they go up to high temperature. This turns out to be, by the way, extraordinarily small amounts of energy. And you go, what? It's like, I'm getting something to like a hundred million degrees. That's going to take the biggest flame burner that I've ever seen. No. And the reason for this is it goes back to the energy content of this. So yeah, you have to, you have to get it to high average energy, but there's very, very few particles. There's low density. How do you get it to be low density in a reactor? So the way that you do this is primarily, again, this is not exactly true in all kinds of fusion, but in the primary one that we work on, magnetic fusion, this is all happening in a hard vacuum. So it's like, it's happening in outer space. So basically, you've gotten rid of all the other particles except for these specialized, so you add them one at a time. No, actually, it's even easier than that. You connect a gas valve and you basically leak gas into it in a controlled fashion. Yeah. </s><s>[INST] It's allowed to be low density and reactors. So you add them one at a time. Well, this is beautiful. [/INST] How do you get the gas cylinder from hitting the walls before? How do you get gas cylinder? Yeah. So now you've touched on the other necessary requirements. So it turns out it's not just temperature that's required, you must also confine it. So what does this mean? </s><s>[INST] Con ins and there's two types of confinement, as [/INST] you mentioned, the magnetic one, magnetic one, there's one we're called inertial as well too. But the general principle actually has nothing to do with, in particular, with what your what with the technology is that you use to confine it. It's because this goes back to the fact that the requirement in this is high temperature and thermal content. So it's like building a fire, man. And what this means is that, when you release the energy into this, or apply heat to this, if it just instantly leaks out, it can never get hot, right? So if you're familiar with this, it's like you've got something that you're trying to apply heat to, but you're just throwing the heat away very quickly. This is why we insulate homes, by the way, and things like this, right? It's like, you don't want the heat that's coming into this room to just immediately leave, you'll just start consuming infinite amounts of heat to try to keep it hot. So, in the end, this is one of the requirements. And it actually has a name. We call the energy confinement time. So, this means if you release a certain amount of energy into this fuel, kind of how long you sit there and you look at your watch, how long does it take for this energy to like leave the system? So, you could imagine that in this room that these heaters are putting energy into the air in this room and you waited for a day what all the heat have gone to outside if I open up the windows. Oh, that's energy confinement time. So it's the same concept as that. So this is an important one. So all fusion must have confinement. There's another more esoteric reason for this, which is that people often confuse temperature and energy. So what do I mean by that? So this is literally a temperature, which means that it is a system in which all the particles, every particle has high kinetic energy and is actually in a fully relaxed state. Namely that entropy has been maximized. I think it's a little bit more technical, but this means that basically it is a thermal system. So it's like the air in this room. It's like the water. It's the water in this. These all have temperatures, which means that there's a distribution of those energies because the particles have collided so much that it's there. So this is distinguished from having high energy particles, like what we have in particle accelerators like CERN and so forth. Those are high kinetic energy, but it's not a temperature. So it actually doesn't count as confinement. So we go through all of those. You have temperature and then the other requirement, not too surprising, is actually that there has to be enough density of the fuel. Enough, but not too much. Enough, but not too much, yes. And so in the end, the way that there's a fancy name for it, it's called the Lawson criterion because it was formulated by scientists in the United Kingdom about 1956 or 1957. And this was essentially the realization, oh, this is what it's going to take, regardless of the confinement method. This is the basic, what it is actually power balance. It just says, oh, there's a certain amount of heat coming in, which is coming from the fusion reaction itself because the fusion reaction heats the fuel versus how fast you would lose it. And it basically is summarized by those three parameters, which is fairly simple. So temperature. And then the reason we say a hundred million degrees is because almost always, for this kind of fusion, deuterium, tritium fusion, the minimum and the density and the confinement time product is at about a hundred million. So you almost always design your device around that minimum. And then you try to get it contained well enough and you try to get enough density. So that temperature thing sounds crazy, right? That's what we've actually achieved in the laboratory. Like our experiment here at MIT, when it ran its optimum configuration, it was at a hundred million degrees, but it wasn't actually the product of the density in the confinement time, wasn't sufficient that we were at a place that we were getting high net energy gain, but it was making fusion reactions. So this is the sequence that you go through, make a plasma, then you get it hot enough. And when you get at hot enough, the fusion reactions start happening so rapidly that it's overcoming the rate that which is leaking heat to the outside world. And at some point, it just becomes like a star, like a sun and our own, our own sun and a star doesn't have anything plugged into it. It's just keeping itself hot through its own fusion reactions in the end that's really close to what a fusion power plant would look like. </s>
<s>[INST] it's going to be a bit more difficult. All right, so that's how it started. [/INST] How did you end up here? How do we end up here? We're in Austin, Texas. I mean, I like to think of Puerto Rico as apocalypse now. John Danaher as Colonel Kurtz. Things got very weird in the jungle and the teams went in two different directions. But honestly, I mean, it's not really my story to tell. I had some issues with some of those people. At the time of the split, I got along very well with John. I feel like me and him connected very well. I don't know why that was. Maybe it was just because he missed home. He missed a familiar accent, Australian New Zealand accent. But I mean, I basically followed Nicky, left with Nicky, sort of that core group of guys left with Nicky. And I mean, I just back, there was personal problems, I just back Nicky basically. </s><s>[INST] Got it. Just sticking on you for a bit. Is there a part of you that, you know, finds it heartbreaking that DDS split up? Does part of you miss working with John and everybody? [/INST] Nick, can you steal man the case for that? I mean, I miss certain aspects of it, but I also do prefer the freedom of being apart from it. It's obviously a very strict regime under John Danaher. You know, obviously there's parts of it. I miss the parts the public doesn't see of John, the behind the scenes banter. I feel like he's very conscious of the image he portrays to the world. But basically it closed doors. He's always making jokes, always finding, I guess more in line with the Australian Kiwi sort of culture. But you don't really see that in the public eye. So that perspective, I do miss that relationship with John. In terms of setting aside personal differences, Gordon was a good training partner. Definitely a good training partner to train with. But obviously the negative things we can't really talk about outweighed all of those things. And we obviously had to make a decision to leave. But yeah. What is that happening in the jungle? The things that happen in the jungle. Should never be spoken of. That I personally cannot speak of. Yeah, but obviously I do miss certain aspects. Like, I mean, nothing's all bad. </s><s>[INST] Nothing's all good, you know? Should never be spoken of. Yeah, this goes back to your like, [/INST] everything we're doing is silly. Yeah, exactly. That's why I don't get people to take it so serious, martial arts so serious. It's just, it's just pretty stupid really. Especially in the gi, it looks just, it looks bad. </s><s>[INST] I mean, it's pretty silly with and without the gi. It's just a bunch of apes. [/INST] What's silly about? It's just a bunch of apes. What's silly about no gi and what's silly about the gi and just mix and match bottoms there. You know what I mean? Wait, which one? Sambo, yeah. I see what you're doing. Brother, you come to my house and offend my people. All right. </s><s>[INST] This is, we're gonna go to every dark place, apparently. Nick, how did you get with DDS? Like, what was that journey like? Is there, try to see if there's things that you remember fondly [/INST] that you've gotten from the experience? All right, so the way I started training with DDS, initially I was training for like, well, initially I was a bouncer, right? I dropped out of college to pursue this fitness modeling career, I ended up signing with the Wilhelmina models up in New York, and I was like, trying to get in better shape. And while I was bouncing, kind of the talk of like, who's tougher came up between the wrestlers and a few of the bouncers that trained jiu-jitsu. And, you know, they convinced me to go to a practice and I went to my first practice over there. And for the most part, I just controlled everybody, got on top of them, was able to avoid like, kind of like, you know, shitty submissions. Cause I had an awareness of the sport and, you know, I'm a fan of fighting and whatnot. So, you know, I kind of understood it pretty well. And then soon after that, I joined a school and my second week of jiu-jitsu, I started competing, had pretty good success. You know, I was like subbing a few black belts and beating everybody like, you know, pretty decisively with points and stuff. And about three months into training locally, I got connected with Gordon Ryan and John Danner up in New York and I committed to, you know, make the drive up there as many days as I could. At the time, I lived in South Jersey and it was about two and a half hour or three hour drive without traffic to New York. Where in South Jersey? Gloucester County, collating New Jersey specifically, but Gloucester County. Yeah, so it was about 130 miles and without traffic, you know, about two and a half hours or so. But on the way back, man, it'd be three plus sometimes, you know, you're catching that rush hour. What year was this, do you remember? </s><s>[INST] This was 2018. This was in 2018. I forget how young you are. Yeah, I was there before all that. All right, cool. Anyway, you're doing the long drive [/INST] and then what, for a bit? Yeah, doing the long drive and then once I won ADCC trials, I was able to make a couple bucks and then I got my silver medal at ADCC and I was able to afford to live up there in New York in North Jersey area. So I lived up there, trained there full time every day and I just kind of sucked with the team throughout the turbulent times and found ourselves in Austin. </s>
<s>[INST] Typical 20th century human with an attachment to this particular singular instantiation of brain and body. How silly humans used to be. He used to have rotary phones and other silly things. You're an incredible human being. You're an educator. You're a researcher. You have an amazing YouTube channel looking to young people if you were to give them advice. How can they have a career that maybe is inspired by yours, inspired by wandering curiosity, a career that can be proud [/INST] of or a life that can be proud of? What advice would you give? I certainly think in terms of a career in science, one thing that I maybe discovered late but has been incredibly influential on me in terms of my own happiness and my own productivity has been this synergy of doing two passions at once. One passion in science communication and another passion research, and not surrendering either one. I think that tends to be seen as something that's an either-or. You have to completely dedicate yourself to one thing to gain mastery in it. That's a conventional way of thinking about both science and other disciplines. I have found that both have been elevated by practicing in each. That's true in all assets of life. If you want to become the best researcher you possibly can, you're pushing your intellect and a sense of your body to a high level. To me, I've always wanted to couple that with training of my body, training of my mind in other ways besides from just what I'm doing when I'm in the lecture room or when I'm in my office calculating something. Focusing on your own development through whatever it is, meditation for me is often running, working out, and pursuing multiple passions provides this almost synergistic bliss of all of them together. So often I've had some of the best research ideas from making a YouTube video and trying to communicate an idea or interact in my audience who've had a question that sparked a whole trail of thought that led down this wonderful intellectual rabbit hole or maybe to a new intellectual discovery can go either way sometimes with those things. So thinking broadly, diversely, and always looking after yourself in this highly competitive and often extremely stressful world that we live in is the best advice I can offer anybody. It's very cheesy, but if you can follow your passions, you'll always be happy. Trying to sell out for the quick cashout, for the quick bookout can be tempting in the short term. Looking for exomoons was never easy, but I made a career not out of discovering exomoons, but out of learning how to communicate the difficult problem, and discovering all sorts of things along the way. We shot for the sky, and we discovered all this stuff along the way. We discovered dozens of new planets using all sorts of new techniques. We push this instrumentation to new places, and I've had an extremely productive research career in this world. I've had all sorts of ideas working on techno signatures. it's thinking innovatively pushes you into all sorts of exciting directions. It's hard to find that passion, but you can sometimes remember it when you're a kid, what your passions were, and what fascinated you as a child. For me, as soon as I picked up a spaceboat when I was five years old, that was it. I was hooked on space, and I almost betrayed my passion at college. I studied physics, which I've always been fascinated by physics as well, but I came back to astronomy because it was my first love, and I was much happier doing research in astronomy than I was in physics because it spoke to that wonder I had as a child that first </s><s>[INST] was the spark of curiosity for me in science. So society will try to get you to look at hot Jupiters, and the advice is to look for the cool world instead. What do you think is the meaning [/INST] of this whole thing? Ever ask yourself why? It's just a ride. It's just a ride. We're on a roller coaster, and we have no purpose. It's an accident in my perspective. There's no meaning to my life. There's no objective deity who is over watching what I'm doing, and I have some fate or destiny. It's all just riding on a roller coaster and trying to have a good time and contribute to other people's enjoyment of the ride. </s><s>[INST] Yeah, try to make it a happy accident. [/INST] Yeah, I see no fundamental providence in my life or in the nature of the universe, and you just see this universe is this beautiful cosmic accident of galaxies smashing together, and stars forging here and there, and planets occasionally spawning, maybe life, across the universe. We are just one of those instantiations, and we should just enjoy this very brief episode that we have. I think trying to look at it much deeper than that, to me, is not very soul </s>
<s>[INST] is not going to make you fluent in science either. And it's interesting, because in that sense you speak many more than three languages, because you're pretty cross-disciplinary. It seems like you have a foot in a lot of disciplines. [/INST] I mean, in machine geology, biology, evolutionary biology, I mean, there's chemistry. Yes, biochemistry, biophysics, even we do a lot of statistics. So there's a lot of mathematics to what we do as well. Yes, we like to think of it as this NASA astrobiology program, I repeat it because it's fun, that it is not a fruit salad, but it's a smoothie. </s><s>[INST] That's what we are generating. It's not a fruit salad, it's a smoothie. [/INST] So a smoothie is a successful combination of those fields, and a fruit salad is not. I wouldn't say success unnecessarily. If you put the wrong ingredient and then you press the blender, you made it a smoothie, </s><s>[INST] you mean it can ruin the entire mix. [/INST] Can it though, because I feel like ever, ever. Yes, I can definitely assess that for ginger, for those that ruin every smoothie. I don't like it. I think so, but it's just a personal thing. And also I don't like cinnamon. </s><s>[INST] Ginger has a cinnamony taste because I thought ginger was... [/INST] No, I don't think they do, but I also don't like it. </s><s>[INST] Wasn't that a thing they add in a lot of smoothies? I was forced a smoothie. I went to Malibu with a good friend of mine, Dan Reynolds, and he forced me to consume a smoothie. And, you know, it was probably the first smoothie I've ever had, because I always had, was very judgmental of the kind of places and people that drink smoothies, [/INST] but it was good, it was good. </s><s>[INST] Well, smoothie is very American, so I... [/INST] Yeah, it is an American thing. I wouldn't say success per se, but it is true that when you dance at the edge of different disciplines, that that's when the inevitably the innovation will rise, because you will see things maybe a little differently when you're on the edge, right? So, but it will probably take longer and it may not be understood right away. It may not come into final form quickly, given that it is a new concept rising. So, therefore, the patients will make more sense, I'm sorry, patients will be even more important. </s><s>[INST] So, if you are, in other words, if you are into immediate appreciation, that's probably not the way to go. You're one chemical organism, so let me ask maybe a little bit more of a personal thing. [/INST] Where did your life form originate and what fond memory do you have from the early days of childhood that are representative of your bacteria culture? I was born in Istanbul, so I grew up in Turkey, a city that has two continents, which is quite interesting. You see a welcome to Europe sign and then welcome to Asia sign, same day, depending on which part of the bridge you are. </s><s>[INST] So, that's where I was born and I spent roughly 20 years of my life and then I immigrated to the United States. It's a very proud culture, it's a beautiful culture, it's a very flavorful culture. [/INST] What aspects of it is part of who you are? What are the beautiful aspects that you carry with you in your heart? I think we are very sincerely human as a culture. I think we have the saying that don't go to bed full if your neighbor is hungry. So, you know, you wouldn't eat any food in front of someone where I come from without offering to share the bite. So, I think those things, however small they may sound, a really big deal, especially when you move to a place that may not have those attributes. So, I think that culturally, there will be a lot of conscious, like you just roll deep human... </s><s>[INST] The connection, the connection between human beings. [/INST] I think so, yeah. I think I definitely carried that with me. </s><s>[INST] We talk a lot about biology. Let me ask you about the romantic question. What role does love play in the human condition or in the entirety of life on Earth? [/INST] It's not easy to learn how to love if you're not loved, okay? But the good news is that it is something that you can learn, I think, that you can practice and teach yourself how to maybe give yourself the thing that wasn't given to you and then ultimately give it to others. I think it would be quite arrogant to think that we will be capable of loving. It could be anything, really. </s><s>[INST] So, just like translation, it's a repeating and a dynamical process. That you can learn. Yeah, that you can learn. [/INST] Yes, and you should learn. There's no excuse to not learning. </s><s>[INST] To love. Because that's a deeply human thing. [/INST] Yeah, it is a deeply human thing. It is a very sad thing if one of us passes this planet without knowing what love is. And that could be allowed to a pet, allowed to a plant. </s><s>[INST] To a robot. Just kidding. Or a fake plant. We love, we can't help who we love. What advice would you give to a young person today? High school, college, how to have a career they can be proud of, or how to have a life? You said an interesting thing about brains being distributed evenly, but opportunity is not. It's really interesting to think about. I've talked to folks from Africa. You realize that there's whole areas of this earth that have so much brilliance, but unfortunately, so little opportunity. And one of the exciting things about the 21st century is more and more opportunities are created. And so, the brilliance is unlocked in all different places. And so, all these young people now have the opportunity to do something to change the world. [/INST] I had a chance to visit Bosnia, so I was invited to give a talk in a very northernmost part of the country that was impacted by the war tremendously. And it was a public talk. It was open to everybody in the village. And I was told even people drew from Sarajevo to attend. Whenever I think about our role as a scientist or the beneficiaries of the knowledge that we create, I always think about that night. That's how many people were in that room. It was incredibly crowded. And lots of young people who were trying to start everything new and not carry, replace whatever, maybe, the feeling that was taken from them with hope and love. Start a new beginning, be the seed for the next generation. </s>
<s>[INST] regular expressions, [/INST] expressions and like some language that was, I don't even know what like ai ml or something, I don't know what that was or something super simplistic all of a sudden was all about potentially actually buildings are the interesting, so I thought there was time and I remember that I talked to my team and I said guys, let's try and my team. And some of my engineers, Russians are Russian and they're very skeptical. They're not, you know, </s><s>[INST] Russians, some of your team is in Moscow, summer, [/INST] summer, some in europe, which </s><s>[INST] team is better? I'm just kidding. Uh the Russians of course, okay, [/INST] the Russians always win. </s><s>[INST] Sorry, sorry to interrupt. So yes, you were talking to them in 2016 and [/INST] I told him, let's build an Ai friend. And it felt just at the time it felt so naive and so um optimistic. That's </s><s>[INST] actually interesting. Whenever I brought up this kind of topic, even just for fun, people of super skeptical, like actually even on the business side, so you were uh because whenever I bring it up to people uh because I thought for a long time I thought like before I was aware of your work, I was like this is gonna make a lot of money. I think there's a lot of opportunity here and people had this like look of like skepticism that I've seen often, which is like how do I politely tell this person he's an idiot. So yeah, you were facing that with your team [/INST] somewhat. Well yeah, you know, I'm not an engineer. So I'm always, my team is almost exclusively engineers. Um, and mostly deploring insurance and you know, I always try to be, it was always hard to me in the beginning to get enough credibility, you know, because I would say, well why don't we try this and that? But it's harder for me because you know, they know their actual engineers and I'm not, so for me to say, well let's build an a friend that would be like, wait, you know, what do you mean? An A G. I like, you know, conversation is, you know, pretty much the hardest, the last frontier before uh cracking that is probably the last frontier before building A J. So what do you really mean by that? Uh, But I think I just saw that again, what we just got reminded of that, you know, that I saw him back in 2012 or 11 that is really not that much about the tech capabilities. It can be metropolitan rick still even with deep learning, but humans need it so </s><s>[INST] much. [/INST] Most importantly what I saw is that finally there's enough tech to made it. I thought to make it useful to make it helpful. Maybe we didn't have quite yet attack In 2012 to make it useful. But in 2015, 16 with deep learning, I thought, you know, and the first kind of thoughts about maybe even using reinforcement learning for that started popping up that never worked out, but or at least for now. Um, but still, the idea was if we can actually measure the emotional outcomes and if we can put it on, if we can try to optimize all of our conversational models for these emotional outcomes and it is the most scalable, the most, the best tool for improving emotional outcomes. Nothing like that exists. That's the most universal. The most scalable. And the one that can be constantly, it's radically changed by itself, improved tool to do that. And I think if anything, people would pay anything to improve their emotional outcomes. That's weirdly, I mean, I don't really care for an ai to turn on my or conversational agent to turn on the lights. Uh, I don't really need it and I don't even need that much of a either like or because I can do that. You know, those things are solved. This is an additional interface for that. That's also questionably questionable whether it's more efficient or better, </s><s>[INST] more possible [/INST] for emotional outcomes. There's nothing there. A bunch of products that claim that they will improve my emotional outcomes, nothing is being measured, nothing is being changed. The product is not being iterated on, based on whether I'm actually feeling better. You know, a lot of social media products are claiming that they're improving my emotional outcomes and making me feel more connected, Can I please get, can I see somewhere that I'm actually getting better over time um </s><s>[INST] because anecdotally doesn't feel that way. So and and the data is absent. [/INST] Yeah, so that was the big goal and I thought if we can learn over time to collect the signal from your users about their emotional outcomes in the long term and in the short term and if these models keep getting better and we can keep optimizing them and fight tuning them to improve those emotional outcomes, let's suppose that </s><s>[INST] why aren't you a multibillion area? [/INST] Well that's a question to you. One of the, one of the side is going to be just um well it's a really hard, I actually think it's an incredibly hard product to build because I think you said something very important that it's not just about machine conversations about machine connection, we can actually use other things to create connection. Non verbal communication for instance, um for a long time we were all about well let's keep it text only or voice only. But as soon as you start adding you know, voice a face to the to the friend um if you can take them to augmented reality, put in your room, it's all of a sudden law, you know, it makes it very different because if it's some you know text based chat bought that for um common user, it's something there in the cloud, you know, somewhere there with other eyes, cloud in the metaphorical cloud. But as soon as you can see this avatar right there in your room and it can turn its head and recognize your husband talk about the husband and talk to him a little bit. And it's magic. It's just magic. Like we've never seen anything like that and the cool thing, all the tech for that exists. Um but it's hard to put it all together because you have to take into consideration so many different things. And some of this tech works, you know, pretty good and some of this doesn't like for instance, speech to tax works pretty good. But text to speech, it doesn't work very good because you can only have uh you know a few voices that are uh that work okay, But then if you want to have actual emotional voices then it's really hard to build it. </s>
<s>[INST] This is one of the task of discovering from human generated data. Strong signals that could be leveraged for self supervision. Like humans are doing so much work already. Like many years ago there was something that was called, I guess human computation back in the day, humans are doing so much work, it would be exciting to discover ways to leverage the work they're doing to teach machines without any extra effort from them. An example could be like we said driving, humans driving and machines can learn from the driving. I always hoped that there could be some supervision signal discovered in video games because there's so many people that play video game that it feels like so much effort is put into video games into playing video games and you can design video games somewhat cheaply to include whatever signals you want. It feels like uh that could be lovers somehow. [/INST] So people are using that. Like there are actually folks right here in Ut Austin. Like Philip Grand Bull is a professor at U. T. Austin, he's been like working on video games as a source of supervision. I mean it's it's really fun. Like as a PhD student getting basically play video games all day. </s><s>[INST] Yeah. But so I do hope that kind of thing scales and like ultimately boils down to discovering some undeniably very good signal. It's like masking in NLP but that said there's non contrasted methods, what do non contrasted energy based self supervised learning methods look like and why are they promising? [/INST] So like I said about contrast of learning, you have this notion of a positive and a negative. Now the thing is this entire learning paradigm really requires access to a lot of negatives uh to learn a good sort of feature space. The idea is, if I tell you, okay, so a cat and a dog are similar and they're very different from a banana. The thing is this is a fairly simple anthology, right? Because bananas look visually very different from what cats and dogs do so very quickly. If this is the only source of supervision that I'm giving you, you're learning is not going to be like after a point that neural network is really not going to learn a lot because the negative that you're getting is going to be so random. So it can be a cat and a dog or similar, but they are very different from a Volkswagen beetle. Now this car looks very different from these animals again. So the thing is in contrast of learning the quality of the negative sample really matters a lot. And so what has happened is basically that typically these methods that are contrasted really require access to lots of negatives, which becomes harder and harder to sort of scale when designing alerting algorithm. So that's been one of the reasons why non contrasted methods have become like popular and why people think that they're going to be more useful. So non contrasted method for example, like clustering is one non contrasted method. The idea basically being that you have to these two of these samples so the cat and dog or two crops of status image, they belong to the same cluster. Uh and so essentially you're basically doing clustering online when you're learning this network and which is very different from having access to a lot of negatives explicitly. The other way, which has become really popular is something called self distillation. So the idea basically is that you have a teacher network and a student network and the teacher network produces of features. So it takes in the image and basically the neural network figures out the patterns, gets the feature out and there's another neural network which is the student neural network and that also produces a feature. And now all you're doing is basically saying that features produced by the teaching network and the student network should be very similar. That's it. There is no notion of negative anymore and that's it. So it's all about similarity maximization between these two features. And so all I need to now do is figure out how to have these two sorts of parallel networks, the student network and a teacher network. And basically researchers have figured out very cheap methods to do this. So you can actually have for free, really two types of neural networks. Uh, they're kind of related but they're different enough that you can actually basically have a learning problem set up </s><s>[INST] so you can ensure that they always remain different enough. So the thing doesn't collapse into something boring. [/INST] Exactly. So the main sort of enemy of self supervised learning, any kind of similarity maximization technique is collapse to a collapse means that you learn the same feature representation for all the images in the world, which is completely useless. </s><s>[INST] Everything is a banana, [/INST] everything is a banana, everything is a cat, everything is a car. Uh And so all we need to do is basically come up with ways to prevent collapse, contrasted learning is one way of doing it. And then for example like clustering or self destination or other ways of doing it. We also have a recent paper where we used like decoration between like two sets of features to prevent collapse. So that inspired a little bit by like Horace Barlas, neuroscience principles </s><s>[INST] by the way I should comment that whoever counts the number of times. Then the word banana, apple, cat and dog were using this conversation wins the internet. I wish you [/INST] luck </s><s>[INST] what what is suave and and the main improvement proposed in the paper unsupervised learning of visual features by contrasting cluster assignments. [/INST] Suave basically is clustering based technique which is for again the same thing for self supervised learning envision where we have to crops and the idea basically is that you want the features from these two crops of an image to lie in the same cluster and basically uh crops that are coming from different images to be in different clusters. Now. Typically in a sort of if you were to do this clustering, you would perform clustering offline. What that means is you would if you have a data set of examples, you would run over all of these examples, get features for them perform clustering, so basically get some clusters and then repeat the process again. So this is offline basically because I need to do one pass through the data to compute its clusters. Suave is basically just a simple way of doing this online. So as you're going through the data, you're actually computing these clusters online. And so of course there is like a lot of tricks involved in how to do this robust manner without collapsing. But this is this sort of key idea to it, </s>
<s>[INST] In this two way communication? Uh is there a way that you could try to describe on a podcast? What is God? What is God like? Uh in your view? Uh uh if you if you try to describe as a force um is it a is it uh for you in intellectually is a set of metaphors that you used to reason about the world? Is it um is it uh is it kind of a computer that does some computation that's infinitely powerful computer? Or is it like santa claus, the guy with the beard on the cloud? Like? Uh I don't mean I don't mean what God actually is. I mean in your limited uh cognitive capacity as a human, what do you actually uh what do you find helpful for thinking of what God actually looks like? What is God? [/INST] Well, let me start by saying none of the above. Okay. I mean clearly God in the christian god um the God of Abraham Isaac and Jacob et cetera. Um it is not any of those things because all of those things you just mentioned are phenomena or or entities in the created world. And the most fundamental thing about monotheism as you know, abraham and moses and so forth, handed it down is that God is not an entity within the creation within the universe, that God is the creator of it all? And that's what genesis first two chapters of genesis is really about, it's not it's not about telling us, you know how God created the world, it's about telling us and telling the early hebrews, that God created the world, okay, and that therefore he is not simply an entity within it. On the other hand, you know, our finite minds have a pretty hard time encompassing that. So, so one has to therefore work in terms of metaphors and images and so forth, and I think we would know very little about who God is. Um if if it was simply, if we were simply left to our own devices, you know, if we were just, you know, here you are, you're in the universe, try to figure out who made it and and so forth. Well, you know, philosophers think they can do a little bit of that, maybe uh and theologians think that they can do a little bit more, but but christians think that God has actually helped us along a lot by revealing himself and and we say that he has revealed himself supremely in the person of jesus christ. Um and so when jesus says to his disciples, if you've seen me, you've seen the father, then that is, in a certain sense, a watchword for answering this question for christians, it is that supremely, if we want to help ourselves understand who God really is, we look to jesus, we looked at what he did, we looked at what he said, uh and so forth, um and uh we believe that he is one with the Father and that's why we believe in the trinity, I mean, it's basically because that revelation is extremely central to christian belief and teaching. </s><s>[INST] So in that, in that sense, through jesus, there was uh that's kind of a historical moment, that's profound, That's really powerful. But do you also think that God makes themselves seen in less obvious ways in our world today? [/INST] Absolutely, Absolutely. I mean, it's it's certainly been the outlook of um jews and christians throughout history that God is seen in the creation that we, when we look at the creation, we see to some extent the wonder, the majesty, the might of the person, the entity, but the person who created it. And that's a way in which scientists particularly have over, over the ages and certainly over most of the last five centuries since the scientific revolution, scientists have seen in a certain sense, the hand of God in creation. I mean, this needs us perhaps to a different discussion, but I mean, it's it's remarkable to me how influential um Christianity and religion and generally has been in science. </s><s>[INST] Yeah, most of the scientists through history as you described. I mean, God has been a very big part of their life and there were certainly [/INST] Up until the 20, at the beginning of the 20th century, that was the case. </s><s>[INST] So maybe this is a good time to, can you tell me what scientist um, is? [/INST] Yeah, I mean, the short answer is that by scientists um we we mean the belief that science is all the real knowledge, there is um that's a shorthand, there are lots of different facets of it and what which one can explore. And in the book in which I explored it most most thoroughly was actually an earlier book called Monopolizing Knowledge. And and the purpose that title is to draw attention to the fact that in our society as a whole, in particularly in the West today we have grown so reliant on science that we that we tend to put aside other ways of getting to know things. And so um of course at MIT we are focused on science and we do um focus on it very much. But the truth is that there are many ways of getting to know things in our world, no things reliably in our world and a lot of them are not science. So scientists um in my view is a terrible intellectual error. It's it's the belief that somehow the methods of science as we've developed them with experiments and in the end they relies particularly upon reproducibility in the world and on a kind of clarity that comes from measurements and mathematics and related types of of skills those powerful though they are for finding out about the world are not all the knowledge do not give us all the knowledge we we have and there's many other forms of knowledge and the illustration that I usually use um to to try to help people to think about this is to say, well look, let's think about human history. I mean, to what extent can human history be discovered scientifically? The answer is essentially can't because and the reason is because human history is not reproducible. You can't do reproducible experiments or observations and and go back and, you know, try it over again. It's a one off thing. You know, the history is full of unique events. And and so, you know, you you you can't hope to do history using the methods of science. </s>
<s>[INST] What about what's your take on unity 2020, that Britain Weinstein uh pushed forward, [/INST] it was D. O. A. Uh he couldn't even stand up to Twitter and on arrival on arrival he couldn't even stand up to Twitter let alone or to Facebook they got blocked let alone two </s><s>[INST] hugely problematic by the way that twitter would block that. [/INST] Not at all. Um I don't know why they blocked it, but I believe I don't know problematic means that's the word, that there's a lot of work that people wanted to do conceptually um the idea that like Unity is like taking the rejects from each party and we're gonna like have something that no one likes and therefore it's going to compromise is absurd. The last time we had this kind of Unity ticket was the Civil war when you had Andrew johnson from the democrats and Lincoln from the republicans. This was not something that ended well, particularly nicely for both halves of the country. </s><s>[INST] So that that's the way you see it as like the way I saw, I guess I haven't looked carefully [/INST] at it. I haven't either, to be fair. Yeah, </s><s>[INST] the way I saw it as emphasizing centrists, which is [/INST] House Tulsi, a centrist </s><s>[INST] Tulsa was involved. Yes, [/INST] he's trying to Tulsa and like jesse ventura or something. </s><s>[INST] So, okay, I don't know. I don't know the [/INST] specific as a scientist. You also know, centrism is not a coherent term in </s><s>[INST] politics. But I see now you're like, uh, what is it pleading to authority? Not [/INST] leading my ego. No, no, I'm pleading to how you approach data. If someone is saying the mean is accurate, that only means, I mean, the mean could be anywhere. It's a function of what's around It doesn't mean. It's true, </s><s>[INST] I don't even know what centrist is supposed to mean, but what it means to me, there's no idea a sense, centrist, there's more of a center right or center left. To me, what that means is somebody who is um a liberal or conservative, but is um open minded and empathetic to the other side, [/INST] joe biden had the crime Bill joe biden voted for Republican Supreme Court justices, joe biden voted for a balanced budget. Joe biden voted for Jeb Bush's war and I'm sure probably I've been looking stuff. The patriot act job. If you want a centrist, you have joe biden. </s><s>[INST] Yeah, he's worked very well with the Republican argument could be made. Of course they'll everybody will always resist [/INST] that argument. It's undeniable. In fact, during the campaign, some um, uh, activists started yelling at him at a town hall, not yelling, just saying, hey, we need open borders, joe biden says, I'm not for open borders, go vote for trump and literally turned his back on the man. And this is during the primaries where it would behoove you to try to appeal to the base. </s><s>[INST] And of course you can probably also make the argument that donald trump is center right, if not center left. [/INST] Well, I mean, he's very, uh, unique as a personality, but if you look at his record and his first name is rhetoric, you can say it's not centrist at all. But in terms of how he governs the budgeting, I mean, has been very moderate. It certainly hasn't been like draconian budget cuts. Uh, the Supreme Court, you could say, okay, he's hard right, immigration, you could say in certain capacities, his hard right. But in terms of pro life, what has he done there in terms of, you know, so it's in many other aspects he's been very much this kind of meat to Republican, but certainly the rhetoric, it's very hard to make the case that he's a centrist. </s><s>[INST] So, you don't like, uh, is there any other idea you find compelling? Like what I like about you and G 2020, is this an idea for a different way for like a different party, a different path forward? So ideas just like anarchy is an interesting idea that that leads to discourse at least. [/INST] I don't think it's interesting at all. And here's why I think it's interesting. Sweden has eight parties in its parliament, Iceland populations like 150,000. They've got nine, I think it was Czech Republic has nine Britain has five. Um, so the claim that two parties is the censorious of speech, but three oh, now, all of a sudden it makes no sense. Doesn't point to the data. Number one. Number two is donald trump demonstrated that you can be basically a third party candidate, sees the machinery of existing party and appropriate to your own hands as Bernie Sanders, almost that Bernie Sanders has never been a democrat. Uh, major credit to him for that's not easy to be elected as senator as an independent. He's done it repeatedly. So, these are two examples of Ossified elites, right? For the picking. So to have a third party makes uh, no real sense. </s><s>[INST] Speaking of which party you talk about quite a bit. Uh, let's like, this is a personal challenge to you. Let me bring up the libertarian party and the personal challenge is to go five minutes without mocking them. Okay, in discussing and discussing this idea. So, first of all, what [/INST] I'm being trolled the troll. Okay, I'm controlled. </s><s>[INST] I'm [/INST] controlled. Okay. Remember the fun friends? There was an episode where Chandler had to not make fun of people like, can you go one day Chandler and Phoebe starts telling him about like this Ufo she saw, and he's like, that's very interesting. Nice </s><s>[INST] for you. This is exactly that. So, a true master would be able to play within the game within the constraints. So, um, no, I'm pretty sure you'll still mock them. But no, [/INST] No, I'll stick to the rules five minutes. </s>
<s>[INST] but that observers embedded and they don't have a complete picture. So [/INST] in the case of physics, that's right, yes. And then in the but that's but so the idea is that in this multi computation set up, that it's this idea of these multiple threads of time and models that are based on that, and this is similar to what people think about a non deterministic computation. So you have a turing machine, usually it has a definite state, it follows another state follows another state. But typically what people have done when they thought about these kinds of things is they've said, well there are all these possible paths and non deterministic turing machine can follow all these possible paths, but we just want one of them, we just want the one that's the winner that factors the number or whatever else. Um and similarly, you know, it's the same story in logic programming and so on, but we say we've got this goal, find us a path to that goal. I just want one path then I'm happy or through improving same story. I just want one proof and then I'm happy. What's happening in multi computation in physics is we actually care about many parts and well, there is a case for example, probabilistic programming is a version of multi computation in which you're looking at all the paths, you're just asking for probabilities of things. Um but in a sense in physics, we're taking different kinds of samplings, for example, in quantum mechanics, we're taking a different kind of sampling of all these multiple parts. But the thing that is notable is that when you are when you're an observer embedded in this thing etcetera etcetera etcetera, with various other sort of footnotes and so on. It is inevitable that the thing that you parse out of the system looks like general relativity and quantum mechanics, um in other words, that just by the very structure of this multi computational setup, it inevitably is the case that you have certain emergent laws now, why is this perhaps not surprising in thermodynamics and statistical mechanics, there are sort of inevitable emergent laws of sort of gas dynamics that are independent of the of the details of molecular dynamics sort of the same kind of thing. But I think what happens is it's a sort of a funny thing that I've just been understanding very recently is When when I kind of introduced this whole sort of computational paradigm complexity ish thing back in the 80s, it was kind of like a big downer because it's like, there's a lot of stuff you can't say about what systems will do and then what I realized is, and you might say now we've got multi computation, it's even worse. You know, it isn't just one thread of time that we can't explain. It's all these threads of time, we can't explain anything. But the following thing happens because there is all this era disability and any detailed thing you might want to answer very hard to answer. But when you have an observer who has certain characteristics like computational bounded nous sequential Galati of time and so on, that Observer only sample certain aspects of this incredible complexity going on in this multi computational system. And that observer is sensitive only to some underlying core structure of this multi computational system. There is all this irreducible computation going on all these details. But to that kind of observer, what's important is only the core structure of multi computation which means that observer observes comparatively simple laws and I think it is inevitable that that observer observes laws which are mathematically structured like general activity and quantum mechanics which by the way are the same law in our model of physics. </s><s>[INST] So that's an explanation why there's simple laws that explain a lot for this Observer [/INST] potentially. Yes. But what the place where this gets really interesting is they're all these fields of science where people have kind of gotten stuck where they say we'd really love to have a physics like theory of economics? We'd really love to have a physics like law and linguistics. </s><s>[INST] You've got to talk about molecular biology here. So where does multi computation come in for biology? Economics is super interesting too. But biology, [/INST] let's talk about that. So let's talk about chemistry for a second. Okay so I mean I have to say you know this is such a weird business for me because you know There are these kind of paradigmatic ideas and then the actual applications and it's like I've always said I know nothing about chemistry. I learned all that chemistry. I know you know the night before some exam when I was 14 years old but I've actually learned a bunch more chemistry and wolfram language these days. We have really pretty nice symbolic representation of chemistry and in understanding the design of that, I've actually I think learned a certain amount of chemistry. So if you quizzed me on sort of basic high school chemistry, I would probably totally fail. But but but okay, so what is chemistry? I mean chemistry is sort of a story of, you know, chemical reactions are like you've got this particular chemical that's representative some graph of you know, these are these are this configuration of molecules with these bonds and so on and a chemical reaction happens. You've got these sort of two graphs. They interact in some way. You get another graph or multiple other graphs out. So that's kind of the the the the sort of the abstract view of what's happening in chemistry. And so when you do a chemical synthesis for example, you are given certain sort of these are possible reactions that can happen. And you're asked can you piece together this a sequence of such reactions, a sequence of such sort of Axiomatic reactions usually called name reactions in chemistry. Can you piece together a sequence of these reactions so that you get out at the end. This great molecule we were trying to synthesize and so that's the story very much like they're improving and people have done actually, they started in the 1960s looking at kind of the fear improving approach to that. Although it didn't really it didn't it didn't it was sort of done too early I think. Um but anyway, so that's kind of the view is that that chemistry chemical reactions are the story of all these different sort of paths of possible things that go on. Okay, let's let's go to an even lower level, let's say, instead of asking about which species of molecules we're talking about. Let's look at individual molecules and let's say we're looking at individual molecules and they are having chemical reactions and we're building up this big graph of all these reactions that are happening. Okay, so so then we've got this big graph and by the way, that big graph is incredibly similar to this hyper graph. Rewriting things. In fact, in the underlying theory of multi computation there, these things we call token event graphs, which are basically you've broken your state into tokens, like in the case of a hyper golf, you've broken it into hyper edges and each event is just consuming some number of tokens and producing some number of tokens. But </s>
<s>[INST] That's all the time. I don't want to place it all in the journalists, I think, because there's a lot of, if I were to think about, what did you call it? Front page thought. There's a lot of really narratives that result in destruction of the human species and nuclear war, pandemics, all that kind of stuff. It seems that climate is a sticky one. So the fact that it's sticky means there's other interests at play like you guys are talking about in terms of politics, all that kind of stuff. So it's not just the journalists. I feel like journalists will try anything for the front page, but it won't stick unless there's bigger interests at play for which these narratives are useful. So journalists will just throw stuff out there and see if it gets clicks and it's like a first spark maybe. It's maybe a tiny catalyst of the initial stuffs, but it has to be picked up by the politicians, by interest groups and all that kind of stuff. Let me ask you about the first part of the subtitle. How climate change panic [/INST] costs us trillions? How does climate change panic cost us trillions? So we're basically deciding to make policies that'll have fairly little impact even in 50 or 100 years that literally cost trillions of dollars. So I'll give you two examples. So the European Union is trying to go to a net zero. So our attempt to go halfway there by 2030 will cost about a trillion dollars a year, and yet the net impact will be almost unmeasurable by the end of the century. Why is that? That's because the EU and the rich countries is a fairly small part of the emissions that are going to come out in the 21st century. Now, we used to be a big part of it. That was mainly because nobody else. It was just the US and Europe and a few others that put out CO2 in the 20th century. So we used to be big, but in the 21st century, we'll be a small bit player. And so we're basically spending a lot of money, and remember, a trillion dollars is a lot of money that could have been spent on a lot of things that could have made humanity better, on something that will only make us tiny bit better. Now, it will do some good, but the reasonable estimates is, if you do a cost-benefit analysis — and, again, technically, it's really, really complicated, but the basic idea is very, very simple. You just simply say, what are all the costs on one side and what are all the benefits? So the costs are mainly that we have to live with more expensive energy. You have to forego some opportunities. You have to have more complicated services, that kind of thing. The benefit is that you cut carbon emissions, and that eventually means you will have less climate damage. You will have lower temperature arises and so on, if you try to weigh all of those, it's reasonable to assume that the EU policies will deliver for every dollar you spend, it'll deliver less than a dollar, probably about 30 cents back on the dollar, which is a really bad way to spend dollars because there's lots and lots of other things out in the world where you could do, you know, multiple, you know, so for instance, if you think about tuberculosis or education of small kids or nutrition for small kids and those kinds of things, every dollar you spend will do like $30 to $100 worth of good. So they're much, much better places where you could spend this money. Likewise, the US is thinking of going net zero by 2050. It's not actually going to happen, but it's sort of a thing that everybody talks about. Biden is talking a lot about it. If you look at the models that indicate how much will that cost, it's not implausible that this will cost somewhere between two and $4 trillion per year by mid century. And remember, if the US went carbon neutral today, by the end of the century, that would reduce temperatures by about 0.3 degrees Fahrenheit. So you would just be able to measure it. It probably wouldn't in real life, but you know, you'd just be able to measure it. Again, this is not saying that there's not some good coming out of it, but you're basically spending an enormous amount of money on fairly small benefits. So that's my main point. Yeah. This reminds me of what we were saying earlier about the things that models don't integrate and the things that cost benefit leave out because you really can't go there. One of the issues facing the world right now is the reality that we're reminded of, that energy availability is a geopolitical destabilizer. If you have uneven access to energy and you have Vladimir Putin coming into office or something else happening that disrupts that system, you're vastly increasing poverty. This is playing out across the world. Fertilizer prices, fertilizer comes from gas, natural gas. If you can envision a world later in the century where we're no longer beholden on this material in the ground, at least fossil fuels, cobalt and lithium for batteries, that's pretty cool because you're taking away geopolysis to political instability. But that's not factored in. That's way outside of what you'd factor in. But it does feel like to me, if I was going to make the case for you can choose your trillions, whatever that investing big isn't for these marginal things. It's for looking at the big picture, a world of abundant energy that doesn't come from a black rock </s>
<s>[INST] So the intelligent constructions of physical systems that would embody the intelligence versus container within the computation. [/INST] Right, and there's a brain centrism that assumes our intelligence is centered in our brain. And in endless ways in this conversation, we've been talking about molecular intelligence. Our molecular systems do a deep kind of artificial intelligence, all the things you think of as artificial intelligence does in representing knowledge, storing knowledge, searching over knowledge, adapting to knowledge our molecular systems do. But the output isn't just a thought, it's us. It's the evolution of us. And that's, the real horizon to come is now embodying AI of not just a processor and a robot, but building systems that really can grow and evolve. </s><s>[INST] So we've been speaking about this boundary between bits and atoms. So let me ask you about one of the big mysteries of consciousness. [/INST] Do you think it comes from somewhere between that boundary? I won't name names, but if you know who I'm talking about, it's probably clear. I once did a drive, in fact, up to the Mussolini-era villa outside Torino in the early days of what became quantum computing with a famous person who thinks about quantum mechanics and consciousness. And we had the most infuriating conversation that went roughly along the lines of consciousness is weird, quantum mechanics is weird, therefore quantum mechanics explains consciousness. </s><s>[INST] That was roughly the logical process. [/INST] And you're not satisfied with that process? No, and I say that very precisely in the following sense. I was a program manager somewhat by accident in a DARPA program on quantum biology. And so biology trivially uses quantum mechanics and that were made out of atoms, but the distinction is in quantum computing, quantum information, you need quantum coherence. And there's a lot of muddled thinking about like collapse of the wave function and claims of quantum computing that garbles just quantum coherence that you can think of it as a wave that has very special properties, but these wave-like properties. And so there's a small set of places where biology uses quantum mechanics in that deeper sense. One is how light is converted to energy in photo systems. It looks like one is olfaction, how your nose is able to tell different smells. Probably one has to do with how birds navigate, how they sense magnetic fields. That involves a coupling between a very weak energy with a magnetic field, coupling into chemical reactions. And there's a beautiful system. Standard in chemistry is magnetic fields like this can influence chemistry, but there are biological circuits that are carefully balanced with two pathways that become unbalanced with magnetic fields. So each of these areas are expensive for biology. It has to consume resources to use quantum mechanics in this way. So again, those are places where we know there's quantum mechanics and biology. In cognition, there's just no evidence. There's no evidence of anything quantum mechanical going on in how cognition works. Consciousness. I'm saying cognition, I'm not saying consciousness, but to get from cognition to consciousness... So McCulloch and Pitts made a model of neurons. That led to perceptrons that then, through a couple of boom busts, led to deep learning. One of the interesting things about that sequence is it diverged off so deep neural networks used in machine learning, diverged from trying to understand how the brain works. What makes them work, what's emerged is, it's a really interesting story. This may be too much of a technical detail, but it has to do with function approximation. We talked about exponentials. A deep network needs an exponentially larger, shallow network to do the same function. And that exponential is what gives the power to deep networks. But what's interesting is the sort of lessons about building these deep architectures and how to train them have really interesting echoes to how brains work. And there's an interesting conversation that's sort of coming back of neuroscientists looking over the shoulder of people training these deep networks, seeing interesting echoes for how the brain works, interesting parallels with it. And so I didn't say consciousness, I just said cognition, but I don't know any experimental evidence that points to anything in neurobiology that says we need quantum mechanics. And I view the question about whether a large language model is conscious as silly in that biology is full of hacks and it works, there's no evidence we have that there's anything deeper going on </s><s>[INST] than just this sort of stacking up of hacks in the brain. And somehow consciousness is one of the hacks [/INST] or an emergent property of the hacks. Absolutely. And just numerically, I said big computations now have the degrees of freedom of the brain. And they're showing a lot of the phenomenology of what we think is properties of what a brain can do. </s><s>[INST] And I don't see any reason to invoke anything else. That makes you wonder what kind of beautiful stuff digital fabrication will create. If biology created a few hacks on top of which consciousness and cognition and some of the things we love about human beings was created. It makes you wonder what kind of beauty in the complexity [/INST] can create as a digital fabrication. There's an early peak at that, which is there's a misleading term, which is generative design. Generative design is where you don't tell a computer how to design something, you tell the computer what you want it to do. That doesn't work, that only works in limited subdomains. You can't do really complex functionality that way. The one place it's matured though is topology optimization for structure. So let's say you wanted to make a bicycle or a table. You describe the loads on it and it figures out how to design it. And what it makes are beautiful organic looking things. These are things that look like they grew in a forest and they look like they grew in a forest because that's sort of exactly what they are, that they're solving the ways of how you handle loads in the same way biology does. And so you get things that look like trees and shells and all of that. And so that's a peak at this transition to from we design to we teach the machines how to design. </s>
<s>[INST] of the plague, you open the book with [/INST] that quote from camus, camus brings me to tears. And it's funny because I reread the myth of Sisyphus, which I've been recommending to people like this book is not good, but he's got his ethos is my favorite of all the philosophers. It </s><s>[INST] sounds like the myth of Sisyphus was a myth. [/INST] He says. All I maintain is that on this earth there are plagues and there are victims and it's up to us so far as possible not to join forces with the plagues and why have that as the introductory quotes the book is I think morality and ethics are very, very complicated subjects. There's lots of gray areas where you don't know which way to choose, but at a base level. He has another quote that subscribed to him, he never actually said, but something about um you know, is the duty of thinking people not to be on the side of the executioners. If you are, we should do whatever we can not to have blood on our hands, not to be murderers, not to want death and that in and of itself is a big pill for a lot of people to swallow were all brought up, taught that war is a last resort and yet when it comes to international affairs, it's always often a first priority and people are champing at the bit to start going in and killing people and what war means isn't good guy soldiers versus bad guy soldiers. It my concern is always with the civilians with the kids who become orphans. With the wives had become widows and and things like that and and then communities which are, you know, ruined forever. Uh so I love that quote of his, I think he's I mean the book start it was going to be a re conceptualization of cameras thought I was going to rip off my old buddy vine holiday what he did with the stoics and do about camus. And then when I started reading camus, I'm like, oh I've read more into him than is really there. And then it went to a whole other direction. Uh </s><s>[INST] so you wanted to do almost like an existentialist manifesto. So like imagine that one must imagine Sisyphus happy [/INST] Well more like a move for today And what his philosophy can teachers like Ryan did with his many books about the stoics </s><s>[INST] that [/INST] it was gonna be called The point of tears </s><s>[INST] lived to the point of tears. [/INST] Yes, but the title was given the point of tears that </s><s>[INST] he [/INST] has so many good lines, maybe it's not </s><s>[INST] right. [/INST] You know, he was a big he was a big lothario. He was probably he got around </s><s>[INST] what [/INST] what </s><s>[INST] percent of the audience of humans on earth do you think? Know the word Lothario? [/INST] What percent them have a computer? Look it up. </s><s>[INST] Lothario. [/INST] It's not some weird term. L O T H A R. I O Lothario </s><s>[INST] Lothario. A man who behaves selfishly and irresponsibly in his sexual relationships with women. They're seduced by handsome quotes. They're seduced by handsome lothario who gains control of their financial affairs. [/INST] I didn't think I always thought it was just someone who's like a stud. </s><s>[INST] Like a player, [/INST] but no player. </s><s>[INST] There's a malevolent, malevolent. [/INST] I didn't realize that. Okay, well then </s><s>[INST] he selfishly. [/INST] Okay, that's not him </s><s>[INST] irresponsibly And a man to um although Iran would be proud selfishly, [/INST] she wouldn't like that kind of selfishness </s><s>[INST] behaves a man who behaves selfishly and irresponsibly in his sexual relationships with women. Huh? Yeah. Okay. So he was he was just a player [/INST] not, maybe maybe a stud. I don't think he was promiscuous, particularly. </s><s>[INST] Nietzsche didn't get he got he didn't never got laid right. He [/INST] was </s><s>[INST] like, it was from [/INST] prostitutes. </s><s>[INST] You're asking me like I knew the guy [/INST] I heard it's </s><s>[INST] from um it he'd never had a deep loving fulfilling relationship. He had a very skewed understanding and uh the way he wrote about women. Although somebody wrote to me and said that's a mischaracterization that he was actually very respectful. [/INST] But he had that line, if you're going before women bring a whip. Wasn't that him? But if </s><s>[INST] I were to quote you from your twitter, I think I could make a very convincing argument that you're sexist, racist and probably a nazi. Well, [/INST] I do own </s><s>[INST] like [/INST] some of Hitler's stuff. </s><s>[INST] Exactly. [/INST] I got the I </s><s>[INST] rest my case. [/INST] I feel like I'm in Nuremberg. I'm gonna be hung by his own tie. This isn't a tie. It's a news. </s><s>[INST] You should have thought about that when you were saying all those things. Okay, what do you think of the leak of the twitter files? [/INST] I was so happy that Ellen gave the information to matt Taibi and Barry? Weiss. Who are both by any metric lefties, </s><s>[INST] who are [/INST] both professional journalists of long standing with great resumes and overnight now they're they're doing pr for the world, which the party line was the fact that you had all these corporate journalists now having to play catch up and not having control of the microphone to me was just absolutely amazing. Um, I think transparency is what brought down in many aspects of soviet union and what will bring down what negative aspects of the regime we have here when you see the machinations behind the scenes. And then when you see the rationalizations after the fact you realize, oh these people are not acting in good faith. The fact that for example, the new york post article about the hunter biden laptop and how the, the new york times covered it as well. They didn't mention any kind of dick pics, twitter made it so I couldn't even DM you the link to the new york post article, which was a tool they had previously used only to prevent child pornography. So that shows to what extent they were willing to put their thumb on the scale. But it also shows that for any layman when they're looking at this, to realize what you are perceiving as news or information is very much sculpted, edited and guided by powerful people who have a vested interest in maintaining their power. </s>
<s>[INST] and basically have the optimism that you have the power to do the change. So, um it's, it's easy to distract yourself by being the critic um that's almost like acknowledging to yourself that that's all you can be. But basically everybody has the power to be the fixer. I like chew glass and look into the abyss. Um That's much more fun than it sounds. What do you think is the meaning of this whole thing? Why are we here? Yeah. What's the meaning of life, what's this existence we got? You're trying to increase the amount of economic freedom on this planet Earth trying to alleviate some of the suffering, but why I [/INST] don't really think there is any point to life. Um You know uh somebody once told me um you know if you go into these like kind of really big existential questions um it can get a little scary because like you stare off the cliff and there's like there's nothing there, you know um one this one person told me one time they were like you know brian you should you should probably snorkel don't scoop. I guess. I think they were trying to say like I and some of my friends have done this right. They will go to like you know epic meditation meditation retreats and like all kind of come back with all this existential dread of like what's the meaning at all. And then like as far as I can tell, we are just some organic molecules in the ocean started like dividing and replicating and the selfish gene and all this stuff like basically ended up here and our only it's it's some kind of like really naive algorithm that's just kind of trying to get us to survive and replicate. And we have D. N. A. Just like every other animal. And so we we happen to develop these like really cool neocortex is. And so now we're sort of self aware and we have all these big questions and maybe maybe we'll create another, you know as computers get better, we'll create the simulation inside our thing and um I think it's cool like we should basically, I just want to keep watching the movie. You know, unfold. That's part of why I want to work on um like new limit is really cool because it's helped if people can live longer whether that's uploading their brain to the cloud or um you know, basically through we get biology to work or the strong ai to work or whatever. One of those two hopefully works out and then we get to we get to keep watching the movie and see how it all unfolds. I think that's fun. And so I don't know if that's like an answer, but I guess I don't think there's any real purpose. So just try to have fun. </s><s>[INST] Well the cool thing is that we get to write the movie as as as we watch it. Yeah, [/INST] that's exactly right. I mean, that's like the steve jobs quote and all that where he's like everything around you was invented by some somebody who just was like that. This is a crazy idea they thought up. So once you realize you can kind of do anything you want um then that's what you start to go do. You start to go try crazier stuff. I mean this is another one of those areas where um not to get too out there, but like, you know when you're when I was I think you can build your comfort zone around like people being upset with you, you can also build your your range of what you think is possible right? Like when I was when I was in my twenties I was like reading all these books about like self improvement and goal right? How to write down your goals and stuff and my goals were like Someday I Wanna make $100,000 a year or something like and that was and you know um and it seemed like a little outlandish or what I wrote down these goals like I want to own rental property or something anyway and and then I slowly started to get some of these things done over a couple of years and so I started a little bigger. </s><s>[INST] I remember [/INST] one time I wrote down this goal where I was like what's the craziest thing I could think of? I was like what if I want to write I want to start </s><s>[INST] a billion dollar tech [/INST] company. That's crazy. And I had I had never started like $1 million dollar tech company or any any tech company really. So what business did I have writing that goal down? Remember I wrote that on a piece of paper like like probably every day for a year or something. Almost right? I don't know it was every day but like I wrote it down a lot and and so little things started to happen I was like all right well maybe I should move back to the Bay area from Buenos Aires maybe I should try to apply to y Combinator or whatever like and I started thinking about these ideas and so whatever gets you fired up it doesn't have to be like some company goal or startup thing. It could be anything right. Um Maybe you want to publish a book or like do something creatively or whatever anyway you know I think like within Seven years uh no it's probably like 10 years of me writing that goal down. Um Columbia's had evaluation over a billion dollars. So it it was out of my realm of what was even possible and then within 10 years you can you can accomplish more than 10 years than you think less than a year than you think. So now I start now I'm like okay what's the next goal? What's the crate? Okay maybe I want to get a billion people accessing the open financial system through our products every day. You know that would be cool for for humanity and that's a pretty crazy goal like there's only eight billion people or something right? So there's one out of eight. Um Or maybe I can radically like if I make some like the right investments or on whatever. I can like help radically extend human health, human health span or whatever right? Um So </s>
<s>[INST] Yeah, I mean, implicit in what you're saying now is a hopeful message that with platforms we can take a step towards greater and greater popularity of truth. But the more cynical view is that what the last few years have revealed is that there's a lot of money to be made in dismantling even the idea of truth, that nothing is true and it's a thought experiment. I've been, you know, thinking about if it's possible that our future will have, like the idea of truth is something we won't even have. Do you think it's possible, but in the future that everything is on the table in terms of truth and we're just swimming in this kind of digital economy where ideas are just little toys that are not at all connected to reality. [/INST] Yeah, I think that's definitely possible. I'm not a technological determinist. So I don't think that's inevitable. I don't think it's inevitable that it doesn't happen. I mean, the thing that I've come away with every time I do these studies and I emphasize it in my books and elsewhere is that technology doesn't shape our destiny, we shape our destiny. So just by us having this conversation, I hope that your audience is going to take it upon themselves as they design their products and they think about their use products as they manage companies. How can they make conscious decisions to favor truth over falsehood, favor the better kinds of societies and not abdicate and say, well, we just build the tools. I think there was a saying that, uh, that was that the german scientists when they're working on the missiles. Um, in late World War Two, you know, they said, well, our job is to make the missiles go up where they come down, that someone else's department. Um, and you know, that's obviously, uh, not that I think it's obvious, that's not the right attitude the technologist should have, that engineers should have, they should be very conscious about what the implications are. And if we think carefully about it, we can avoid the kind of world that you just described where truth is all relative, there are going to be people who benefit from a world of where people don't check facts and where truth is relative and popularity or fame or money, um, is orthogonal to truth, But one of the reasons I suspect that we've had so much progress over the past few 100 years is the invention of the scientific method which is a really powerful tool or meta tool for finding truth and favoring things that are true versus things that are false. If they don't pass the scientific method they're less likely to be true. And uh that has the societies and the people and the organizations that embrace that have done a lot better um than the ones who haven't. And so I'm hoping that people keep that in mind and continue to try to embrace not just the truth but methods that lead to the truth. </s><s>[INST] So maybe on a more personal question, if one were to try to build a competitor to twitter, what would you advise? Is there? Uh I mean I mean the bigger the better question is that the right way to improve systems? [/INST] Yeah. No I think that the underlying premise behind twitter all these networks is amazing that we can communicate with each other and and I used it a lot. There's a sub part of twitter called icon twitter where you know we economist tweet to each other and and talk about new papers. Something came out in the N. B. E. R. National Bureau of Economic Research and we share about people critique it. I think it's been a godsend because it's really sped up the scientific process if you can call economic scientific </s><s>[INST] get divisive and that little [/INST] sometimes. Yeah sure sometimes it does, it can also be done in nasty ways and you know, there's a bad parts, but the good parts are great because you just speed up that clock speed of learning about things, you know, instead of like an old old days, you know, waiting to read in the journal or the not so old days when you see it posted on a, on a website and you'd read it now on twitter, like people will distill it down and there's a real art to getting to the essence of things. So that's been great. Um, but um, it's certainly we all know that twitter can be a cess pool of misinformation and like I just said, unfortunately, misinformation tends to spread faster on twitter than truth and there's a lot of people who are very vulnerable to it. I'm sure I've been fooled at times. There are uh, agents whether from Russia or from political groups or um, others that explicitly create efforts that misinformation and efforts at getting people to hate each other or even more important lately I've discovered is, is not picking, you know, the idea of not picking up the good term nut picking is when you find like an extreme nutcase on the other side and then you amplify them and make it seem like that's typical of the other side. So you're not literally lying, you're taking some idiot renting on the subway or just, you know, whether they're in the KKK or antifa or whatever, they just And you normally nobody would pay attention. This guy, like 12 people would see, I'm going to be the end instead with video or whatever you get tens of millions of people said. And I've seen this, you know, I look at it, I get angry, like I can't believe that person did something so terrible. Let me tell my friends about this terrible person. Uh and it's it's a great way to generate division. I talked to a friend who studied Russian misinformation campaigns and they're very clever about literally being on both sides of some of these debates. They would have some people pretend to be part of BLM, some people pretend to be white nationalists and they would be throwing epithets at each other saying crazy things at each other and they're literally playing both sides of it, but their goal wasn't for one or the other to win, it was for everybody to get to hating and distrusting everyone else. So these tools can definitely be used for that and they are being used for that. It's been super destructive for our democracy in our society and the people who run these platforms, I think have a social responsibility, a moral and ethical, personal responsibility to do a better job and to shut that stuff down as well, don't You can shut it down, but to design them in a way that that, you know, as I said earlier favors truth over over falsehoods and favors positive types of um communication versus destructive ones, </s>
<s>[INST] system. I wonder if there's other improvements that take us into the 21st century that allow for electronic voting. There's all kinds of improvements that seems our system is dragging their feet [/INST] on, ranchers, voting, all that kind of stuff. Let's make this clear. We claim to be the greatest 21st century democracy and we still vote like the 19th century. We're not even in the 20th century. Most people, when they went to vote, they actually checked a box and put a piece of paper in a box. That's not 21st century. We can move millions of dollars, maybe billions for you, Lex, in bank accounts from our keyboards. Thank you. From our keyboards. Billions of rubles. Billions of pennies. Pennies. Why can we move money safely and not vote in the same way? </s><s>[INST] Yeah. From our keyboard. And at the same time, so there's security there in the movement of money and then there's the actual engagement. Most of us, depending on your age demographic, click like on Facebook or Twitter or TikTok, tens of thousands of times a year. I think this kind of mechanism of costly and alike is a vote. So you're constantly voting, voting, voting, voting. We love voting. We love giving our opinion on that stuff. It just seems obvious that gamifying the system, which is essentially what the election is, making it fun to be engaged in different issues. And there's also be a case, now I don't understand these things deeply, but it always seemed to me that issue-based voting should be the future. It seems like too complicated to vote for singular people versus on ideas, which on Twitter, we don't necessarily vote for people. We vote for ideas. If you like a tweet or not, you like it and so on. That too seems [/INST] to be like a possibility for improvement. Well, there's certainly a way to improve polling. We could measure public opinion better. We still poll as if we're in the early 20th century. They still actually call people. It's amazing to me. I was talking to one pollster. They will call a hundred people and get one person, but they still do that. They probably still call landlines, right? Yeah. Well, they try to get cell phones too, but they do call landlines. But one could create a system that would be far better in the way you're describing, it seems to me, Lex, to actually assess what people like and don't like. </s><s>[INST] Probably still... Yeah. Well, they try to get... So your book, your work in general, your perspective on history is, I would say, at least from my perspective, nonpartisan. Thank you. Yeah, you do an exception. Good job with that, despite the attacks and the criticisms. That said, you personally, just the way you speak, my judgment, and you can push back on this, I think you lean left in your politics on the political spectrum. Maybe you can push back on that. Can you make the case for either perspective on your own personality as a fan [/INST] of yours that you do lean left or you don't lean left? So I think it depends on the kinds of issues we're talking about. I do tend to lean left on the social and cultural issues. So I'm a believer, a firm believer. I didn't believe this when I was younger. I've come to believe that people should choose their own lifestyle and that we should get out of the way. I'm a believer, deep believer, as a father of a 20-year-old woman, that my 20-year-old daughter should have the right to make any choice she wants with her body. And if she were to get pregnant at a fraternity party at college, she should have the right to decide whether to have a child or not. So on those issues, that would code me left of center. I'm actually reasonably conservative on fiscal issues. I don't think we should spend money we don't have. I've long been skeptical of cryptocurrency and things like that. I know some of your listeners will disagree with me on this part. It's part of my own ignorance of cryptocurrency. But I'm conservative, lowercase c, in the way I think about fiscal issues. I worry about debt. I'm a believer that there are certain areas where the federal government should play more of a role. And there are other areas where things should be left to the localities. And so sometimes that can code me one way or another. But I think I sound sometimes a little more left </s><s>[INST] of center because on the social issues, I definitely. Well, there's other explanations not to be grilling you too hard here. No, it's fair. Because you're also an exceptionally respected and successful professor in the university system, where sometimes there is a lean towards the left. And the other aspect is, I think your viewpoints on Trump, where you're a strong critic, Donald Trump. And I guess the question I want to ask is, you as a historian, does that color your perspective of history? Do you ever catch yourself where maybe your criticism of Donald Trump might affect how you see the Civil War? As you were completely diving in and looking at the Civil War, are you able to put aside the current day political viewpoints? [/INST] No, I'm not. I think we have to be honest that none of us are objective. We strive to be nonpartisan. I really liked when you said that, because I think it's an aspiration. No one is objective. We all have our biases. Some people like chocolate, some like vanilla. And that's just the reality, right? And as far as I know, it's very hard even to biologically explain that. And so my view is that what a good historian, what a good scholar does, I don't care what the field is, is you're self-conscious of your biases and you try to recognize them as you're doing your research. And you make doubly certain that where your research seems to reinforce your biases, that you actually have the evidence to make that argument. But I still believe even doing that, that someone with a slightly different perspective might read the same evidence in different ways. That's what makes history vibrant. So I wrote this book in part, as I say in the introduction, because I was self-critical watching Trump and the things I quite frankly find deeply dangerous about Donald Trump and about what happened on January 6th. And I found I had not thought deeply enough about the roots of that in our society, because I don't believe Trump or any one figure creates </s>
<s>[INST] So, I have to ask, this is this kind of an interesting question. The X marking A for many people, including myself is one of the greatest ai films ever made. It's number two for [/INST] me. Thanks. Yeah, it's definitely not one. It was number one, I'd really have to Well, anyway, yeah, whenever you </s><s>[INST] grow up with something, right, When we grow up with something, it's it's in the blood. Uh, but there's um one of the things that people bring up, you can't please everyone, including myself. This is what I first reacted to the film is the idea of the lone genius. This is the criticism that people say sort of me as an irish or I'm trying to create what what what Nathan is trying to do. So there's a brilliant, serious culture noble. [/INST] Yes, it's fantastic. Absolutely </s><s>[INST] spectacular. I mean, I mean, they got so many things brilliant, all right. But one of the things, again, the criticism there [/INST] create inflated lots of people into </s><s>[INST] one character that represents all nuclear scientists. They wanna come back? Uh, it's uh composite character that presents all scientists. Is this what you were? Is this the way you were thinking about that? Or is it just simplifies the storytelling? How do you think about the lone genius? [/INST] Well, I'd say this, the series I'm doing at the moment is a critique in part of the lone genius concept. So yes, I'm sort of oppositional and either agnostic or atheistic about that as a concept. I mean, not entirely, you know, uh, with a loan loan is the right word broadly isolated. But Newton clearly exists in a sort of bubble of himself in some respects. So does Shakespeare. And </s><s>[INST] do you think we would have an iphone without steve jobs? How much [/INST] emotion from jobs clearly isn't a lone genius because because there's too many other people in the sort of superstructure around him who are absolutely fundamental to to that journey. </s><s>[INST] But you're saying Newton, but that's a scientific, so there's an engineering element to building Eva [/INST] but just to say what X mechanism is really, it's a thought experiment. I mean, so it's a construction of putting four people, uh, in a house. Uh, nothing about X. McKenna adds up in all sorts of ways. Inasmuch as that. Who built the machine parts? Did the people building the machine parts, know what they were creating and how did they get there. And it's a thought experiment. So it doesn't, it doesn't stand up to scrutiny of that sort, </s><s>[INST] I don't think it's actually that interesting of a question, but it's brought up so often that I had to ask it because that's exactly how I felt after what, you know, there's something about, there was almost a different, like I washed your movie the first time in at least for the first little while in a defensive way. Like how dare this person try to step into the Ai space and try to beat kubrick, that's the way I was thinking, like, because because it it comes off as a movie that really is going after the deep fundamental questions about AI. So there's a, there's a kind of a, you know, nerds do, so it gets automatically searching for the for the flaws and it's [/INST] exactly the same, I </s><s>[INST] think annihilation and the and the other movie, the, I would be able to free myself from that much quicker that it's a, it is a thought experiment, There's you know, who cares if there's batteries that don't run out right, those kinds of questions, that's the whole point. [/INST] But uh </s><s>[INST] it's nevertheless something I wanted [/INST] to bring up, it's a it's a fair thing to bring up for me that you you hit on the lone genius thing for me, it was actually people always said hex McKenna makes this big leap in terms of where Ai has got to and also what a I would look like if it got to that point, there's another one which is just robotics. I mean look at the way Eva walks around the room, it's like forget it, building that that's that's that's also got to be a very, very long way. Often if you did get there wouldn't look anything like that. It's a thought experiment. </s><s>[INST] Actually agree with you. I think that the way as a ballerina, Alicia Vikander, brilliant actress, uh, actor that moves around that were very far away from creating that. But the way she moves around is exactly the definition of perfection for roboticists, it's like smooth and efficient. So it is where we want to get, I believe like I I think so. I hang out with a lot of like humanoid robotics people, they love elegant, smooth motion like that, that's their dream. So the way she moved is actually what I believe they would dream for a robot to move. It might not be that useful to move that sort of uh, that way, But that is the definition of perfection in terms of movement, drawing inspiration from real life. So for for Dev's forex McKenna look at characters like Elon musk, what do you think about the various big technological efforts of Elon musk and others like him and that he's involved with such as Tesla SpaceX neuralink, do you see any any of that technology potentially defining the future worlds you create in your work. So Tesla's automation, SpaceX's SpaceX operation neuralink is brain machine interface somehow merger of biological and electric systems. [/INST] I'm in a way I'm influenced by that almost by definition because that's the world I live in and this is the thing that's happening in that world and I also feel supportive of it. So I think, I think amongst various things Elon musk has done, I'm almost sure he's done a very, very good thing with Tesla for all of us. Um, it's really kicked all the other car manufacturers in the face. It's kicked the fossil fuel industry in the face and they needed kicking in the face and he's done it. So, and so that's the world he's part of creating and I live in that world. Um, just bought a Tesla in fact. And so, uh, does that play into whatever I then make in some ways it does partly because I try to be a writer who quite often filmmakers are in some ways fixated on the films they grew up with and they sort of remake those films in some ways. I've always tried to avoid that. And so I looked at the real world to get inspiration and as much as possible sort of by living, I think. And so, so yeah, I'm sure </s>
<s>[INST] But throughout the day, you're doing a lot of really in-depth classes. So how do you either prepare for them or think through them as they're happening? [/INST] Think through the material that you're teaching. I can look at a class. I've been doing this a long time. So I can just look at a class and be like, okay, these guys need this, this, and this. And then I make reflections at the end of the day. Then I'll take care of things that we all do, talk to family, occasionally go out for dinner with friends, dates, things like that. </s><s>[INST] Yeah, Hanzo had to really harass you to drag you out and to hang out. And he was very convincing. [/INST] And food-wise, I eat once a day. He wants a day. At the end of the day, I usually stop off at a place like a supermarket, like Whole Foods or some equivalent </s><s>[INST] to that, and buy something simple and eat. The internet wants to know the details. Did you end up getting wifi for your apartment? [/INST] No, no, I'm still thinking about it. It's a... Yeah, what are the pros and cons? There's no cons, lots of pros, but I just don't put much importance to it, </s><s>[INST] things that are unimportant, I just ignore. Yeah, there's a lot of things in life that have a lot of pros, but they're lower on the priority list, why? Why, because the 5G already... 5G's got it covered. Do you watch much video? Do you watch video? [/INST] Do you watch footage? Video footage, quite often, yeah. Especially things from freestyle wrestling, record Roman wrestling, judo, and mixed martial arts. Also, subsidiary sports to mixed martial arts, </s><s>[INST] like boxing, Muay Thai and European kickboxing. Just for long-term idea generation. Yes. Like a plan to seed an idea. [/INST] Yeah, this is an interesting thing. How could this be incorporated in the context in which we use it, MMA or Judas? </s><s>[INST] Maybe it's immediately obvious, or it might become obvious in a few weeks or months. Is there some aspect to the way you approach life and training and martial arts that amends itself to minimalism? It seems like you live a pretty stoic life. [/INST] Or is that just a symptom of a focus of existence? My life wasn't always like this. I've gone through different phases in my life. I was a university student and teacher at university. I was a nightclub bouncer for more than a decade. I've been through different areas of life. I've seen most things, I've experienced a lot. I've traveled the world. At this point in my life, people think I live some kind of monk-like existence, but I have a private life. I like to go out and have fun like everyone else. I'm not some kind of monk who just sits under a waterfall </s><s>[INST] and meditates or anything crazy like that. Well, that's why. I'm currently going through that stage in my life, the monk-like existence. So I would be amiss not to ask you one of the most important questions one can possibly ask John Donohue, which is on the topic of animal combat. Who wins in a fight to the death? Or maybe in a sport competition setting, but let's go with a fight to the death. A grizzly bear, a silverback gorilla, and maybe a lion or a tiger, an African lion, or one of the flavors of tiger. I don't know who you think is more ferocious. What are the parameters to consider here? Maybe I can throw a few out and maybe you can give me some thoughts about how much of these parameters matter. So first of all, intelligence. I do believe the gorilla is the most intelligent. I've did research for this, as you could imagine. The expert advisor to this very podcast on this very topic is indeed Joe Rogan, yes. So in captivity, gorillas have been documented to show complex emotions, form family bonds, the ability to use tools, [/INST] and to be able to reason about the past and the future. </s><s>[INST] That's impressive. So that's something that, at least in captivity, the other animals have not been able to do. [/INST] They already sound much more advanced than I am. </s><s>[INST] Yeah, so that's intelligence. Then there is weight. I think that's something that you think of at first. The lion, let's go with the big ones. I took notes here, 550 pounds for big lion. [/INST] That's exceptionally large. Most male lions are around 450 pounds. What's an exceptional beast then? </s><s>[INST] Thank you. The tiger can be larger than that. Yeah, much larger. So we got the grizzly bear, which is probably the biggest of the bunch. The large ones get to 1,500 pounds. Correct me if some of this numbers. [/INST] I believe most grizzlies are around 1,000 pound mark. </s><s>[INST] It's a big, big, big beast. Well, I was looking up the biggest, but I didn't want to do the biggest ever. Just what are the big, like the top of the range [/INST] because there's always a range. You can put it in at roughly double </s><s>[INST] that of even a very big lion. Of course, how that weight is used is very important. So there's also things which I find as interesting as anaconda, which just, let me throw that in there because it's 200 pounds. What I really like about that is it's not just the weight, it's the form factor. And I think out of all of these, the anaconda is the most non-standard form factor. I totally agree with that. [/INST] Yeah, I totally agree with that. It's like the knight on the chessboard. </s>
<s>[INST] I mean, her sense in your sense are we just uh this is the question of mathematics. So we just kind of an introductory thru rule real space, except in mathematics through trajectory, a certain kind [/INST] of uh that's partly the idea. So, so I think that the notion is this. So 100 years ago a little bit more than 100 years ago, What people have been doing mathematics for ages. But then in the late 1800s, people decided to try and formalize mathematics and say, you know, it is mathematics is, you know, we're going to break it down, we're gonna make it like logic, we're going to make it out of out of sort of fundamental primitives and that was people like Frogger and piano and Hilbert and so on. And they kind of got this idea of let's do kind of euclid, but even better, let's just make everything just in terms of this sort of symbolic axioms and then build up mathematics from that and that, you know, they thought at the time as soon as they get these symbolic axioms that they made the same mistake, the kind of computational reproducibility mistake, they thought as soon as we have written down the axioms, then it'll just we'll just have a machine kind of a super mathematica, so to speak, that can just grind out all true theorems of mathematics that got exploited by girdles serum, which is basically the story of computational irreducible itty. It's that even though, you know, those underlying rules, you can't deduce all the consequences in any finite way. And so that was. But now the question is, okay, so they broke mathematics down into these axioms and they say now you build up from that. So what I'm increasingly uh coming to realize is that similar to saying, let's take a gas and break it down into molecules, there's gas laws that are the large scale structure and so on that we humans are familiar with. And then there's the underlying molecular dynamics. And I think that the axiomatic level of mathematics which we can access with automated theorem proving and proof assistance and these kinds of things. That's the molecular dynamics of mathematics. And occasionally we see through to that molecular dynamics, we see underside ability, we see other things like this. One of things I've always found very mysterious is that girdles serum shows that there are sort of things which cannot be finite. We proved in mathematics, there are proofs of arbitrary length, infinite length proofs that you might need. But in practical mathematics, mathematicians don't typically run into this. They just happily go along doing their mathematics. And I think what's actually happening is that what they're doing is they're looking at this. They are essentially observers in meta mathematical space and they are picking a reference frame in meta mathematical space. And they are computational rebounded observers of meta mathematical space, which is causing them to deduce that the laws of mathematics and the laws of mathematics, like the laws of fluid mechanics are much more understandable than this underlying molecular dynamics. And so what gets really bizarre is thinking about kind of the analogy between meta mathematics, this idea of of you exist in this kind of uh in the sort of space of possible um in this kind of mathematical space where the where the individual kind of points in the in the mathematical space are statements in mathematics. And they're connected by proofs where one statement, you know, you take a couple of different statements, you can use those to prove some other statement and you've got this whole network of proofs. That's the kind of causal network of mathematics of what can prove what and so on. And you can say at any moment in the history of a mathematician of a single mathematical consciousness, you are in a single kind of slice of this kind of math, a mathematical space. You, you know, a certain set of mathematical statements, you can then deduce with proofs, you can deduce other ones and so on. Your kind of gradually moving through mathematical space. And so it's kind of the view is that the reason that mathematicians perceive mathematics to have the sort of integrity and lack of kind of underside ability and so on that they do is because they like we as as observers the physical universe. We have these limitations associated with computational bounded Nous single thread of time consciousness limitations basically that the same thing is true of mathematicians perceiving sort of math mathematical space. And so what's happening is that when you look at, if you look at one of these formalized mathematics systems, something like, you know, pythagoras theorem. It'll be it'll take, oh, I don't know, uh what is it? Maybe 10,000 individual little steps to prove Pythagoras theorem. And one of the bizarre things that's sort of an empirical fact that I'm trying to understand a little bit better. If you look at different prophecies, that if you look at different formalized mathematics systems, they actually have different axioms underneath, but they can all prove pythagoras theorem. And so in other words, it's a little bit like what happens with gasses, we can have air molecules, we can have water molecules, but they still have fluid dynamics. Both of them have fluid dynamics and so similarly at the level that mathematics that mathematicians care about mathematics, it's way above the macular dynamics, so to speak. And there are all kinds of weird things. Like, for example, one thing I was realizing recently is the quantum theory of mathematics. That's a very bizarre idea. But basically, when you prove what is, you know, a proof is you've got one statement in mathematics, you go through other statements, You eventually get to a statement you're trying to prove, for example, that's a path path. In meta mathematical space and that's a single path, A single proof is a single path. But you can imagine there are other proofs of the same results there, a bundle of proofs. There's this whole set of possible proof, </s>
<s>[INST] as [/INST] social beings that we have an honest report? </s><s>[INST] That's hard to uh hard to control. But is it, is it well understood what, how that connects to internal state of emotion? [/INST] There are long range projections that come. So where where is crying generate. This is the confusing thing about it so that we have a little tear duct, the lack criminal gland that leads to the release of fluid and ejects fluid. And it comes out. And those of course that whole system was designed to keep the eye clean to to wash out particulate irritants. So it's it's a long standing, as long as we've had eyes and have been out of the water. Uh in our evolution we've needed this sort of thing. So longstanding biological structure recently co opted, it seems by our evolution as social primates. Now, how could that happen? Well, the lack criminal gland is controlled by structures in the ponds which is a structure deep in our just above our neck, between our neck and our head and reflecting its ancient origin right as you go farther down toward the spinal cord. These are the more basic early evolved structures and and in the ponds. That's where breathing is controlled to your uh doctor uh contraction. And what we found with optogenetics. We helped sort this out. There are long range projections from fear and anxiety regions in the forebrain that project all the way to the ponds in and around those areas. The reason those are there we think is to regulate the respiratory rate changes. The breathing changes of fear and anxiety. So we know when we're in a state of fear and anxiety we need, we cope better if we have elevated heart rate, elevated respiratory rate, more blood pumping around more oxygenated blood. We're ready to meet the threat if it happens, all those cells are down there in the ponds to right next to the lack of duct, the tear gland neurons. And so almost certainly this okay fear, anxiety induced crying arose from a very slightly misdirected long range projection that was there to regulate breathing and a little twist, just a little misdirection, a little missing of one sign post to stop here and going on a little farther getting to the lachrymose gland neurons </s><s>[INST] and that's and we just have it that the peculiar sort of structure, neuronal structure that resulted in that that's that's that's what we're stuck with and then and ends up being in terms of social interaction. One of the more important, authentic involuntary displays of [/INST] interstate and </s><s>[INST] social communication. Oh yeah. Is there other stuff like that? I mean, do you Yeah, I mean the human face is fascinating as a display of emotion as a display of truth and lying and all those kinds of things. I personally, I mean we're all I suppose have different uh sensors that are sensitive to certain aspects of the human face. But to me it seems like the eyes are really important communication or something. You know I've talked to a few sort of girls about like Botox and stuff like that. It always bothers me when I guess guys can do this too, but like when women um speak negatively of, I guess you can call them wrinkles at the, at the tips of of an eye, but like to me when you smile when you wait, not wink, but like narrow the eyes to community, something that's communicated and those, that stuff is really useful human face and when it's gone that something is missing and a lot of little stuff it feels like and really it's almost involuntary I guess, but it's harder to describe as the presence or absence of tears. It's like something about this person you can tell they're not bullshitting [/INST] you. And so that was, that was what made presumably that, that tear recruitment so powerful is that just landed in this very high value real estate for social communication. If it had gone to, you know, there's a lot of neurons in the, in the ponds that control, you know, movement of large, you know, muscles, you know, elsewhere that would have been much less effective as a social signal than something around the eye. So it was however, that that little misdirection happened. It it landed in a great area for social communication and because it was coming from the fear and anxiety circuits that regulate that necessary involuntary change in heart rate and respiratory rate. It also was involuntary and that became valuable as a, as a truth signal as social beings. So very interesting when you think about the origins of the human family, origins of social structures and our ability and need to call for help when there's hope, but but need at the same time, </s><s>[INST] what is consciousness? So you're actually using techniques, I mean, even putting psychiatrists are just looking at optogenetics, you're trying to understand some of these deep aspects of the human mind and maybe this is a good time to return to a question you mentioned. You might have an opinion on if there's such a thing as a theory of everything for the human mind. Because surely answering of what is consciousness is as well, that's not sure. But it seems like it's a fundamental part of the human experience in the human mind and solving that question or the result in solving the bigger thing about the human mind. The flip side could be consciousness. It's just a few neurons that are generating some useful things that make us, it's like uh the the sense of self that you talked about in the in the mice, maybe it's a subset of those cells that are just creating a richer sense of self. And that's it. [/INST] So this is a great question all neuroscientists think about this and a lot of non neuroscientists to it's it's such a it's the reason a lot of people came to the study of the brain is to think about consciousness and not just being awake or alert, but really what's sometimes called the hard problem of consciousness, which is what is that nature of that inner subjective sense? We have not just information processing but feeling something about the information that what is that inner state of subjectivity, physically, what is it? And that's called the hard problem of consciousness. And it's not extremely well defined question. Everybody has sort of a sense of what it means. But </s>
<s>[INST] when you look at when you take a bigger picture. Yeah. So, uh, the writing process, uh, is it fundamentally lonely. So, no, [/INST] because you're with your characters, </s><s>[INST] you are, so you really put yourself in the world [/INST] absolutely. You know, uh I've written about this before that I used to have my desk used to face a wall instead of seeing and people would say, well don't you want to look out the window, but I'm in here. I mean, I'm seeing, you know, the Spartans, I'm seeing, you know, whatever and The characters that are on the page or that you create are not accidents. You know, they're coming out of some issue, some deep issue that you have, whether you realize it or not, you might not realize until 20 years later or somebody explains it to you. So, your characters are kind of fascinating to you and their dilemmas are, are fascinating to you and you're also trying to to um come to grips with them, you know, you sort of see them through a glass darkly, you know, and you really want to see them more clearly. Um, so yeah, no, it's not lonely at all. In fact, I'm more lonely sometimes later, going out to dinner with some people and actually talking to people, </s><s>[INST] do you miss the characters after it's over? [/INST] Uh, let's say I have, I have affection for them, kind of like Children that have gone off to college and now are, you know, you only see him at thanksgiving. Uh definitely I have affection for him. Even the bad guys, maybe, </s><s>[INST] especially the bad guy, [/INST] especially the bad guys. </s><s>[INST] Uh you've said that writers, even successful writers are often not tough minded enough. I've read that in the post, that you have to be a professional in the way you handle your emotions. You have to be a bit of a warrior to be a writer. So what are, what do you think makes a warrior? Is that as a warrior born or trained in the realm, in the bigger realm, in the realm of writing, in the creative process? [/INST] I think, I think they're born to some extent you have the gift, like, you might have a gift as a martial artist to do whatever martial artists do, but the training is, is the big thing, 90% training 10% 10% genetics and uh you know, I use another analogy other than Warrior two as far as writers and it's like to be a mother, if you think about if you're a writer or any creative person giving birth to something that you're carrying a new life inside you and in terms of bravery, if you're child, your two year old child is underneath, a car is coming down the street, the mother's gonna like stop a buick, you know, with their bare hands. So that's a that's another way to think about how how a writer has to think about or any creative person has to think about, I think what they're what they're doing, what this this child, this new creation that they're bringing forth. </s><s>[INST] Yeah, so the hard work that's underlying that I've just a couple weeks ago talked to just happened to be in the same room, both gave talks Arianna Huffington, I did this conversation with her uh I didn't know much about her before then, but she has recently been short a couple of books have been promoting a lifestyle Where she basically she created a Huffington post and she gave herself like, I don't know, 20 hours a day, just obsessed with her work. And then she she fainted passed out and kind of uh there was some health issues and so she wrote this book saying that, you know, sleep basically you want to establish a lifestyle that doesn't sacrifice health, that's productive but doesn't sacrifice health. She thinks you can have both productivity and health criticizing Elon musk who have also spoken with for working too hard and thereby sacrificing, um you know, being less effective than he could be. So I'm trying to get this balance between health and obsessively working at something, I'm really working hard. So what Ariana is talking about, it makes sense to me, but I'm a little bit torn to me, passionate reason do not overlap much or at all sometimes, uh, maybe I'm being too Russian, but uh, I feel madness and obsession does not care for health or sleep or diet or any of that and hard work, it's hard work and everything else can go to house. So if you're really focused on whether it's writing a book and it should, everything should just go to hell. Uh where do you stand on this balance? How important is health for productivity? How important is it to sort of get sleep and so on? [/INST] I'm from on the, on the health side. Uh I mean, there was a period of my life when I was just uh uh had no obligations and I was just living in a little house and just working nonstop, you know, but even then I would get up in the morning and I would have liver and eggs for breakfast every day and I would do my, you know exercise whatever it was, but although I was still doing like, you know, 18 hours a day, but I I'm definitely, yeah, I kind of think of it sort of like an athlete does, I'm sure that like Steph curry um is totally committed to winning championships and stuff like that. But he has his family, he sees his fan, you know, family is always there. He I'm sure he eats, you know, perfect, great stuff, gets asleep, you know, gets the the train, you know, whatever a trainer does to him for his knees and his ankles and whatever. So I or Kobe Bryant or anybody that's uh it's operating at a high level. So I do think I'm from that kind of the health school, the good thing about being a writer is you can't work very many hours a day, you know, four hours is like the maximum I can work. I've never been able to work more than that. I don't know how people do it. I've heard of people do 10, 12, I don't know how they do it. So that gives you a lot of other time to </s>
<s>[INST] But that's a complete natural emergence of a theory of mind. But I feel like if you add a little bit of a place for a theory of mind to emerge, like easier than um, you can go really far. I mean, some of these things with evolution, you know, you add a little bit of design in there, it will really help. And I think I tend to think that a very simple theory of mind will go a really long way for cooperation between agents and certainly for a human robot interaction, like it doesn't have to be super complicated. And I've gotten a chance to in the autonomous vehicle space to watch vehicles, interact with pedestrians or pedestrians interacting with vehicles in general. I mean you would think that there is a very complicated theory of mind thing going on. But I have a sense it's not well understood yet, but I have a sense it's pretty dumb. Like it's pretty simple. There's a social contract, there were between humans, a human driver and a human crossing the road where um the human crossing the road trust that the human and the car is not going to murder them. And there's something about again, back to that mortality thing. There's some dance of ethics and morality that's built in that you're mapping your own morality onto the person in the car. And even if they're driving at a speed where you think if they don't stop, they're going to kill you. You trust that if you step in front of them, they're going to hit the brakes and there's that weird dance that we do that I think is a pretty simple model. But of course it's very difficult to introspect what it is and autonomous robots in the human robot interaction context have to have to build that current robots are much less than what you're describing there. Currently just afraid of everything. They're they're more, they're not the kind that fall and discover how to run their more like please don't touch anything, don't hurt anything. Stay as far away from humans as possible to treat humans as ballistic objects that you can't that you do a with a large spatial envelope, make sure you do not collide with. That's how like mentioned Elon musk thinks about autonomous vehicles. I tend to think autonomous vehicles need to have a beautiful dance between human and machine or it's not just the collision avoidance problem but a weird dance. [/INST] Yeah, I think these systems need to be able to predict what will happen, what the other agent is going to do and then have the structure of what the goals are and whether those predictions actually meet the goals and you can go probably pretty far with that relatively simple set up already. But we call it a theory of mind. I don't think you need to, I mean it doesn't matter whether pedestrian has a mind, it's an object and we can predict what we will do and then we can predict what the states will be in the future and whether they are desirable states stay away from those that are undesirable and go towards those that are desirable. So it's a relatively simple functional approach to that. Where do we really need the theory of mind? Um Maybe maybe when you start interacting and you're trying to get the other agent to do something and jointly so that you can jointly collaboratively achieve something. Then then then it becomes more complex. Well, I mean even </s><s>[INST] with the pedestrians you have to have a sense of where their attention actual attention in terms of their gaze is but also like a tent. There's this vision science people talk about the Sultan just because I'm looking at it doesn't mean I'm paying attention to it. So figuring out what is the person looking at, what is the sense of information they've taken in And the theory of mind peace comes in is what are they actually attending to cognitively. And also what are they thinking about? Like what is the computation they're performing? And you have you have probably maybe a few options, you know for the pedestrian crossing, it doesn't have to be like a variable with a few discrete states. But you have to have a good estimation which of the states that brain is in for the pedestrian case. And the same as for attending with a robot. If you're collaborating to pick up an object, you have to figure out is the human like uh like there's a few discrete states that the human could be. And you have to you have to predict that by observing the human and that seems like a machine learning problem to figure out uh what's how the human is, what's the human up to. It's not as simple as sort of planning just because they move their arm means the arm will continue moving in this direction. You have to you have to really have a model of what they're thinking about and what's the motivation behind [/INST] the and here we are talking about relatively simple physical actions, but you can take that the higher levels also like to predict what the people are going to do. You need to know what what their goals are uh what are they trying to the exercising and they understand to get somewhere. But even even higher level, I mean you are predicting what people will do in their career, what their life themes are. Do they want to be famous rich or do good and and that takes a lot more information. But it allows you to then predict their their actions, what choices they might make. </s>
<s>[INST] Well I tend to believe just a small little change agent like I'm with Ernest Becker on this that there's some, it's interesting to think about death and consciousness. Which one is the chicken? Which one is the egg? Because it feels like death could be the very thing like our knowledge of mortality could be the very thing that creates consciousness. [/INST] Yeah. Well then you're using consciousness differently than than I am. So so for me consciousness is just the fact that the lights are on at all that there's an experiential quality to anything. So much of the processing that's happening in our brains right now seems certainly seems to be happening in the dark, right? Like it's not associated with this qualitative sense that there's something that's like to be that part of the mind doing that mental thing. Ah but for other parts the lights are on and and we can talk about and whether we talk about or not we can feel directly that there's something that is like to be us. There's something something seems to be happening, right? And this seeming in our case is broken into vision and hearing and appropriate reception and uh taste and smell and and thought and emotion and there's there are the contents of consciousness uh that we are familiar with and that we can we can have direct access to in any present moment that when we're quote conscious and even if we're confused about them, even if you were asleep and dreaming and we really and where it's not a lucid dream, we're just totally confused about our circumstance. What you can't say is that we're confused about consciousness. You can't say that consciousness itself might be an illusion because on this account, it just means that things seem any way at all, even like this, you know, it seems to me that I'm seeing a cup on the table now, I could be wrong about that. It could be a hologram, I could be asleep and dreaming, I could be hallucinating. But the seeming part isn't really up for grabs in terms of being an illusion. It's not something seems to be happening. And that's seeming is that is the context in which every other thing we can notice about ourselves can be noticed. And it's also the context in which certain illusions can be cut through because we're not we can be wrong about what it's like to be us and we can I'm not saying we're incorrigible with respect to our claims about the nature of our experience, but for instance, this, you know, many people feel like they have a self and they feel like it has free will. And, you know, I'm quite sure at this point that they're wrong about that and that you can you can cut through those experiences and then things seem a different way, right? So it's not that it's not that things don't, there are discoveries to be made there and assumptions to be overturned. But um this kind of consciousness is something that I would think it doesn't just come online when we get language. It doesn't just come online when we form a concept of death or, you know, the finite nous of life. It doesn't it doesn't require a sense of self, right? So it doesn't it's prior to a differentiating itself and other ah and I wouldn't even think it's necessarily limited to people. And I do think probably any uh mammal has this, but certainly if you're going to if you're going to Presuppose that something about our brains is producing this, right? And that's a very safe assumption. Even though we can't, even though you can argue the jury is still out to some degree, then it's very hard to draw a principled line between us and chimps, you know, or chimps, and and, you know, rats, even in the end, given the underlying neural similarities. So, um, and I don't know, you know, file it genetically, I don't know how far back to push that, you know, they're people, you know, think single cells might be conscious or that, you know, flies are certainly conscious. They've got something like uh 100,000 neurons in their brains and says, it's just that's a there's a lot going on even in a fly, right? Uh but I I don't have intuitions about that, </s><s>[INST] but it's not in your sense, an illusion you can cut through. I mean, to push back the alternative version could be it is an illusion constructed by just by humans. I'm not sure I believe this, but part of me hopes this is true because it makes it easier to engineer is that humans are able to contemplate their mortality. And that contemplation in itself creates consciousness. That like the the rich lights on experience. So the lights don't actually even turn on in the way that you're describing until after birth, in that construction. So, do you think it's possible that that is the case that it is a sort of construct of the way we deal almost like a social tool to deal with the reality of the world, social interaction with other humans, or because you're saying the complete opposite, which is it's like fundamental to single cell organisms and trees and and and so on. [/INST] Well, yeah, I I don't I don't know how far down to push it. I don't have intuitions that single cells are likely to be conscious, but uh but they might be and I just again, I could be unfalsifiable. Um but as far as babies not being conscious, you're not, you don't become conscious until you can recognize yourself in a mirror or you have a conversation or treat other people. First of all, babies treat other people as others far earlier than we have traditionally given them credit for. And they certainly do it before they have language. Right? So it's, it's a, it's got to proceed language uh, to some degree and you can interrogate this for yourself because you can put yourself in various states that are, uh, rather obviously not linguistic. You know, you know, meditation allows you to do this. You can certainly do it with psychedelics where it's just your capacity for language has been obliterated and yet you're all too conscious. In fact, uh, I think you could make a stronger argument for things running the other way that there's something about language and, and conceptual thought that is eliminated of conscious experience. That we're, we are potentially much more conscious of data sensed data and everything else than we tend to be. And we have trimmed it down based on how, how we have acquired concepts. And so like when I walk into a room like this, I know I'm walking into a room, I have certain expectations of what is in a room. You know, I would be very surprised to see, you know, wild animals in here or waterfall or things I'm not expecting. But I can, no, I'm not expecting them or I'm expecting their absence because of my capacity to be surprised once I walk into a room and I see it, you know, a live gorilla or whatever. So there's there's structure there that we have put in place based on all of our conceptual learning and language and language learning and it causes us not to. One of the things that happens when you take psychedelics and you just look as though for the first time at anything it becomes incredibly overloaded with uh it can become overloaded with meaning and and ah just the the torrents of sense data that are coming in and even the most ordinary circumstances can become overwhelming for people And that tends to just obliterate one's capacity to capture any of it linguistically. And and as you're coming down right, have you done psychedelics? We've ever done acid or </s>
<s>[INST] So is there something about the putting the responsibility on the president to to form the structure around him locally such that he can make the policy that that matches the rhetoric. So what I'm talking to is hiring. So basically just everybody you work with, you have power as president to fire and hire or to basically schedule meetings in such a way that can control your decision making. So I imagine it's very difficult to to get out of Afghanistan or Iraq when most of your scheduled meetings are with generals or something like that. But if you reorganize the schedule and you reorganize who you have like late night talks with you potentially have a huge ripple effect on the, on the policy. [/INST] I think that's right. I think who has access to the President is absolutely crucial and presidents have to be more strategic about that. They tend to be reacting to crisis because every day has a crisis and if you're reacting to crisis, you're not controlling access because the crisis is driving you. So that's one element of it. But I also think and this is the moment we're in right now, presidents have to invest in reforming the system, the system of decision making. Should we have a National Security Council that looks the way it does. Should our military be structured the way it is, the Founding Fathers wanted a military that was divided. They did not want to unified a Department of Defense that was only created after World War Two. Should we have as large a military as we have. Should we be in as many places? There are some fundamental structural reforms we have to undertake and part of that is who you appoint. But part of that is also how you change the institutions. That the genius of the american system is that it's a dynamic system. It can be adjusted. It has been adjusted over time. That's the heroic story. The frustrating story is, it often takes us a long time to make those adjustments until we go into such bad circumstances that we have no choice. </s><s>[INST] So in the battle of power of the Office of the President versus the United States Military, the Department of Defense. Do you have a sense that the President has more power ultimately? So to decrease the size of the Department of Defense to withdraw from any wars or increase the amount of wars is the President, You're kind of implying the President has a lot of power here in this scale? [/INST] Yes, the President has a lot of power and we are fortunate and it was just proven in the last few years that our military, uniquely among many countries with large militaries is very deferential to the President and very restricted in its ability to challenge the president. Um So that's the strength of our system but the way you reform the military is not with individual decisions. It's by having by having a strategic plan that re examines what role it plays. So it's not just about whether we're in Afghanistan or not. The question we have to ask is when we look at our toolbox of what we can do in our foreign policy, are there other tools we should build up and therefore some tools from the military we should reduce. That's the broader strategic question. </s><s>[INST] Let me ask you the most absurd question of all that you did not sign up for. But it's especially I've been hanging out with a guy named Joe Rogan recently. So it's very important um For from for me and him to figure this out if a president because you said you implied the president's very powerful if the president shows up and and the U. S. Government is in fact in possession of aliens, alien spacecraft. Do you think the president will be told a more responsible adult historian question version of that? Is is there some things that the machine of government keeps secret from the president or is the president ultimately at the very center? So if you like map out the set of information and power. You have you have like CIA you have all these organizations that like that do the the machinery of government. Not just like the passing of bills but like uh gaining information. Homeland security actually like engaging in wars. You know, all those kinds of things. Uh how central is the president? Would the president knows some of the shady things that are going on aliens or some kind of cyber security stuff against Russia and china all those kinds of things. Is the president really made aware And how if so how nervous does that make you? [/INST] So um presidents like leaders of any complex organizations uh don't know everything that goes on. They have to ask the right questions. This is Machiavelli. The most important thing a leader has to do is ask the right questions. You don't have to know the answers. That's why you hire smart people. But you have to ask the right questions. So if the president asks uh the U. S. Government, those who are responsible for the aliens are responsible for the cyber warfare against Russia, they will answer honestly. They will have to but they will not volunteer that information in all cases. So the best way a president can operate is to have people around him or her who are not the traditional policymakers. This is where I think academic experts are important suggesting questions to ask two. Therefore try to get the information. </s><s>[INST] It makes me nervous because I think human nature is such that the academics, the experts, everybody is almost afraid to ask the questions for which the answers might uh be burdensome. Yes and so right. And you can get into a lot of trouble not asking. It's the old elephant in the room, [/INST] correct, correct. This is exactly right. And too often mediocre leaders and those who try to protect them, try to shield themselves. They don't want to know certain things. So this is part of what happened with the use of torture by the United States, which is a war crime. Um, during the war on terror, President Bush at times intentionally did not ask and people around him prevented him from asking or discouraged him from asking questions he should have asked to know about what was going on and that's how we ended up where we did. You could say the same thing about Reagan and Iran contra. </s>
<s>[INST] So celebration of humanity and a kind of gratitude [/INST] for having traveled quite a long way to get here. And if you look at the diversity of topics as well, I mean, we had a school teacher present on teaching immigrants, a book called Making Americans. We had a presidential advisor to four different presidents come and talk about the changing of US politics. We had a musician, a composer from Italy who lives in Australia come and present his latest piece and fundraise. We had painters come and sort of show their art and talk about it. We've had authors of books on leadership. We've had intellectuals like Steven Pinker and it's just extraordinary that the breadth and this crowd basically loves not just the diversity of the audience, but also the diversity of the topics. And the last few were with Scott Aronson on AI and alignment and all of that. So a bunch of beautiful weirdos </s><s>[INST] and beautiful human beings. And beautiful human beings. And just like you said, basically every human is a kind of outcast in this sparse distribution far away from the center, but it's not recorded. It's just a small human gathering. In this world that seeks to record so much, it's powerful to get so many interesting humans together [/INST] and not record. </s><s>[INST] It's not recorded, but it percolates. It's recorded in the minds of the- It shapes everyone's mind. So allow me to please return to the human condition and one of the nice features of the human condition is love. Do you think humans will fall in love with AI systems and maybe they with us? So that aspect of the human condition, [/INST] do you think that will be affected? So in Greece, there's many, many words for love. And some of them mean friendship. Some of them mean passionate love. Some of them mean fraternal love, et cetera. So I think AI doesn't have the baggage that we do and it doesn't have all of the subcortical regions that we kind of started with before we evolved all of the cognitive aspects. So I would say AI is faking it when it comes to love. But when it comes to friendship, when it comes to being able to be your therapist, your coach, your motivator, someone who synthesizes stuff for you, who writes for you, who interprets a complex passage, who compacts down a very long lecture or a very long text, I think that friendship will definitely be there. Like the fact that I can have my companion, my partner, my AI who has grown to know me well and that I can trust with all of the darkest parts of myself, all of my flaws, all of the stuff that I only talk about to my friends and basically say, listen, here's all this stuff that I'm struggling with. Someone who will not judge me, who will always be there to better me. In some ways, not having the baggage might make for your best friend, for your confidant that can truly help reshape you. So I do believe that human AI relationships will absolutely be there, </s><s>[INST] but not the passion, more the mentoring. Well, it's a really interesting thought to play devil's advocate. If those AI systems are locked in in faking the baggage, who are you to say that the AI systems that begs you not to leave it? It doesn't love you. Who are you to say that this AI system that writes poetry to you, that is afraid of death, afraid of life without you, or vice versa, creates the kind of drama that humans create, the power dynamics that can exist in a relationship. What AI system that is abusive one day and romantic the other day, all the different variations of relationships, and it's consistently that it holds the full richness of a particular personality. Why is that not a system you can love in a romantic way? [/INST] Why is it faking it if it sure as hell seems real? There's many answers to this. The first is it's only the eye of the beholder. Who tells me that I'm not faking it either? Maybe all of these subcortical systems that make me sort of have different emotions, maybe they don't really matter. Maybe all that matters is the neocortex, and that's where all of my emotions are encoded, and the rest is just bells and whistles. That's one possibility. And therefore, who am I to judge that it's faking it when maybe I'm faking it as well? The second is neither of us is faking it. Maybe it's just an emergent behavior of these neocortical systems that is truly capturing the same exact essence of love and hatred and dependency and sort of, you know, reverse psychology and that we have. So it is possible that it's simply an emergent behavior and that we don't have to encode these additional architectures, that all we need is more parameters, and some of these parameters can be all of the personality traits. A third option is that just by telling me, oh look, now I've built an emotion component to AI. It has a limbic system, it has a lizard brain, et cetera. And suddenly I'll say, oh cool, it has the capability of emotion. So now when it exhibits the exact same unchanged behaviors that it does without it, I as the beholder will be able to sort of attribute to it emotional attributes that I would to another human being, and therefore have that mental model of that other person. So again, I think a lot of relationships is about the mental models that you project on the other person and that they're projecting on you. And then yeah, then in that respect, I do think that even without the embodied intelligence part, without having ever experienced what it's like to be heartbroken, the sort of guttural feeling of misery, that that system, I could still attribute it </s>
<s>[INST] It's kind of interesting, I don't know if you can comment on, especially for me growing up in Russia, it's probably true in a lot of cultures, maybe every culture that food and especially like in the family, the mother that cooks is the source of love and like ties the family together. It creates events where everyone comes together. It's uh it's one of the only chances of togetherness of the thing that bonds of family is like dinner or eating together. And I don't know what to do with that. It ties up with like dieting and so on. When I was on stricter diet, especially competing and cutting weight and stuff, it felt like I was almost like losing opportunity to connect with friends and family. It's interesting. It's almost like cultures, we cannot fully experience love and family without eating. And on the flip side of that eating enables us to experience love and family. I don't know what to do with that. [/INST] It's a tough one because there's lots of layers around kind of gender roles and um families changing and things. I'd say I agree around the alienation and I've done carnivore diet and I've tried some of these extreme protocols and I too, I suffered from loneliness, you know, it was like doing carnivore and and not being able to eat what my kids eight and talk about it at the same time, those pieces are real and I wonder with all of these diets if that structure is actually helping or just taking away from people's kind of sensual understanding. Um, but I think that there's some rigor around that, that helps people discover what's good for them by eliminating and then growing towards more intuitive food is a good evolution from that base. I love to cook for people. I love to pay attention to their their way of being and read what they'd like to eat. And it's my, my purest way of love and that's for everybody in my life. I actually love to cook for people. I love, you know, I don't, I would have struggled to be, you know, putting out food all the time. It's like something for me, it's a real act of caretaking. So I definitely have that in my makeup. Um and, and I definitely notice um in times of like of, of real stress, that's the piece that drops off right then then and it's like if I'm unable to care for myself, I have a hard time cooking. So it's, for me it's very emotional, it's very connected to love </s><s>[INST] and individualistic. So like focused on the particular individual, it's almost like a journey of understanding what that person is excited about in the, in the landscape of flavors, like figuring that person out what they like, what they, what they love to eat. Yeah, I see cooking from, I mostly cook for myself. So I see that it's almost a, okay, this is gonna be like the worst term, but like an act of self [/INST] love, </s><s>[INST] uh this is going to be clipped out uh that like it's almost an exploration of like what brings me joy and it's surprising because I usually don't share because the things that bring me joy are the simplest ingredients, like I'm one of those people, I don't know if you can psychoanalyze me because you also like basic ingredients. I like a single ingredient, two ingredients because I feel like I can deeply appreciate the particular ingredient. Then I get easily distracted. You know, people who are really good listening to music, they can hear a piece of music and in their mind extract the different layers and enjoy different layers at a time. Like the bass, the drums, the different layering of the piano, the beats and all that kind of stuff. That's what it means to truly enjoy music to listen to a piece over and over. Like almost like as a scholar in that same way for food, I just can't do more than like three because then it's just I have to give in to the chaos of it I guess. But when it's just the basic ingredients like just meat and we're just a vegetable like basic grilled without sauces without any of that that I've discovered is what brings me a lot of joy, but that's boring to a lot of people. So I usually have to be kind of private about that joy. So, but that's mine. So I figured that out and I guess as a, as a chef, you have to figure that out about everybody that you care for [/INST] well. Also for you, you're very interested in things and, and interested in things being done well and appreciating them. So the single ingredient also allows you to control for perfection and cooking that which is probably really appealing to you. Um And I think sometimes I see people also in the beginning of their journey of culinary trying to do too many things, right? So there's another piece to that. You'll notice if you recall last night I grilled us the salad, right? And then I did all those pieces separately. And that's something in general to be really attentive of when you're building flavor to make sure you pay attention to every piece separately. Um You know the idea that you can okay with the soup or something or stew? There's, there's workarounds, but like to make a great dish that's got four or five vegetables in it, Cook them all separately to their optimal deliciousness and then combine them. So that's another way to approach that is that you may also be able to look at the different ingredients separately and still have that sense of like understanding of it. But there's too often that we're layering together like four or 5 things and then cooking them all at once and then surprised that it's not delicious because you can't, you can't really optimize on multiple variables at the same time for peak awesomeness and that's actually, you know, the number one way you see this is roasting a whole chicken, which is a really difficult. That's the simplistic, but it's very difficult because you have the breast meat, which is bigger chunks. They cook faster. You have the thighs and drums which are um smaller and they cook slower to optimize that and pay attention to it and do it all right there, you're actually solving for different outcomes. So there's a, there's one example, but oftentimes food is less delicious with multiple ingredients. The start because we're not able to pay attention to how each one needs to end up. So there's a way to parse that apart and achieve a better outcome. </s>
<s>[INST] hearing that and hearing Metallica master of puppets, I was like, I knew I'm gonna have to end up in America one day. I mean maybe now that I'm more mature or maybe a little bit more mature. I realized like that was kind of the longing for freedom. It felt like at least at the time if this is allowed that anything is allowed. And I think that uh the rebellion of it the um I guess it's also fun. I just I just loved it. Is there if you look back to that because you're you're I mean you were that person not just the producer. It feels like [/INST] well yes and no like it was even to us then it was still like satirical. You know, it was absolutely </s><s>[INST] but isn't like music in part like you're dancing on the line. It's part satirical part serious in a sense. Like you're losing yourself in this satire. Like when you ever anytime you go over the top isn't that part of the or is it this is it explicitly satirical? You're making fun. I mean girls and there's a lot of ridiculous songs on that album. [/INST] I don't know. I just think it's it was definitely to make each other laugh. Like we were trying to make each other laugh. We weren't trying to make a point. We're trying to make each other laugh. </s><s>[INST] But that person how's that person different than the person today and you the person I wouldn't [/INST] say so different. Like it really is that that um I like things that make me laugh, you know, I like ridiculous things, I think so </s><s>[INST] it's a strange, just how many incredible, [/INST] I mean I wouldn't I don't think I would make that today, but I understand why we made it when we did. It's a in the vocabulary of, of ridiculous, that would make sense to do, you know, for the right artist today could make something ridiculous and gives you that feeling. </s><s>[INST] I mean there's just a sense when you make so many different albums, then you look back at that creation and it can feel like a different person created that. But you're making it seem like if you travel back in time and maybe do a memory replay, you'll be able to hang out with with the teenage In the 20s recruitment? [/INST] I don't think, I don't think I was so different. Honestly, </s><s>[INST] it's [/INST] funny, I ran into someone um recently in Costa Rica who I hadn't seen in a long time and who I knew from the new york days when those days and and we spent a couple of hours talking and she said you're exactly the same person that you were then. So I have a short, you know, a recent confirmation that that's the case </s><s>[INST] that's beautiful, was it tim Ferriss asked you about like who is the most successful person, you know, that's the definition of success. I would say it's exactly the same person, you haven't lost yourself or rather you found yourself early on. [/INST] I would say there are aspects of me that have changed for sure. Um, but I, but I can't say that it's that it's necessarily better. It's different. Um, at that I would say at that time I was more confident than I am now and I'm very confident now. But then I had an unrealistic um, confidence and I think now it's a little more based in reality at that point in time, I had never been depressed and then once you go through a depression. Yeah. Well some people I know in my case and when I went through depression afterwards, I was a different person than I was before. And I feel more um grounded now than I did then. And I probably relate to the artists who, so many of the artists I work with suffer. So many artists suffer because that's part of what makes an artist great. Is there level of sensitivity? That that's the same thing that makes uh, an artist uncomfortable? Other people don't feel at all </s><s>[INST] the time. You're the press. What was the darkest moments of your life? What took you there? How did you get out? [/INST] It was triggered by a person making a comment about something to do with work that didn't matter. You know, it was like, uh to anyone else, they would hear that and it would just be like, okay, we'll deal with it next week, whatever, But for some reason I took it in a way that I felt like the rug had been pulled out from under me even beyond the rational part of it of understanding, you know, even after the problem that came up was solved it somehow undermine something in me and made me feel very vulnerable in a way that I hadn't felt before </s><s>[INST] and it spiraled, how did you get out? [/INST] I did a lot of different kinds of therapy I did um starting with alternative therapies I was seeing, I would say Between seven and 8 doctors and your therapists a week. Um acupuncture, talk therapy, herbs, any any possible modality, tried everything for a long time and um and nothing seemed to have an impact. And then finally um I'm wary of taking any Western medicine. I'm not a drug taker and or drinker partier in any way. And um I found a psychopharmacologist who is a psychic but because she was a psychic, I was okay to see her because like I'll do I'll listen to a psychic but I'm not gonna listen to a psychopharmacologist. But the fact that she had the psychic that made her fit into my world view and um and she recommended antidepressant which went terribly wrong in the first night that I took it. And then I that set me on a journey of looking for the right antidepressant which was a long and painful process. Everyone that I took made me sick everyone. And then finally said, I don't know, five months later, six months later I found the Magic one that worked for me. And it um it shifted me out of the depression. I took it for, I can't remember six months or a year and then weaned off and was okay. And then I had another event some years later, I think I took it again for a short period of time and got out of it and I've not needed it since </s>
<s>[INST] concrete terms, It's a very [/INST] concrete I mean, they're just things like, you know, uh logical. Aw </s><s>[INST] right, But that's the thing. That's a powerful thing. [/INST] Well, it's yes. Okay. But it's it's a the point is that it is not a thing about, you know, people imagine there is, I don't know, the uh you know, an elephant or something or the, you know, elephants are presumably not necessary objects. They are they happen to exist as a result of kind of biological evolution and whatever else. But the thing is that in some sense that there is it is a different kind of thing to say does plus exist? The it's not not not like an elephant. So, </s><s>[INST] plus it seems more fundamental, more basic than an elephant. Yes, But you can imagine a world without plus or anything like it, like why do formal things that are discreet? That can be used to reason have to exist or uh well, okay, [/INST] so why? Okay, so then the question is, but the whole point is computation. We can certainly imagine computation. That is we can certainly say there is a formal system that we can construct abstractly in our minds. That is computation. And that that's the uh you know, we can we can imagine it right now. The question is um is it is that formal system once we exist as observers embedded in that formal system, that's enough to have something which is like our universe. And so then the then what you're kind of asking is perhaps is why, I mean, the point is we definitely can imagine it. There's nothing that says that we're not saying that uh it's sort of inevitable that that is a thing that we can imagine. We don't have to ask, does it exist? Where just it is definitely something we can imagine now that then we have this thing that is a formally construct herbal thing that we can imagine. And now we have to ask the question, what, you know, given that formerly construct herbal thing, what is what consequences does that if we were to perceive that formally, if we were embedded in that formally construct herbal thing, what we perceive about the world, and we would say we perceive that the world exists because we are we are seeing all of this mechanism of all these things happening. And but that's something that is just a feature of. It's something where we are. See another way of </s><s>[INST] asking this, I'm trying to get at. I understand why it feels like this rule yod is necessary, but maybe it's just me being human, but it feels like then you should be able to not us, but somehow step outside of the rule of God? Like what's outside the really odd? [/INST] Well, the ruling out is all formal systems. So there's nothing because that's what a human would say. I know that's what a human would say because we're used to the idea that there are there's but the whole point is that by the time it's all possible formal systems, it's like it is all things you can imagine, but all </s><s>[INST] computations you can imagine, but like we don't [/INST] well, so that we could be a code. Okay, so so that's a that's a fair question. Is it possible to encode all? I mean, once we, is there something that isn't what we can represent formally that, is that is is there something that and that's I think related to the hyper really odd footnote, so to speak of them, which I'm afraid that the, you know, one of the things sort of interesting about this is, you know, there has been some discussion of this in theology and things like that, um but which I don't necessarily understand all of um but the the key sort of new input is this idea that or possible formal systems, It's like, you know, if you make a world, people say, well, you make a world with a particular in a particular way with particular rules, but no, you don't do that, you can make a world that deals with all possible rules and then merely by virtue of living in a particular place in that world, so to speak, we have the perception we have of what the world is like now, I have to say the the uh it's sort of interesting because I've I've, you know, I wrote this piece about this and I, you know, this philosophy stuff is not super easy. And I've, uh, as I'm, as I'm talking to you about it and I actually haven't, you know, people have been interested in lots of different things we've been doing. But this, why does the universe exist has been, I would say one of the, one of the ones that you would think people would be most interested in. But actually, I think they're just like, oh, that's just something complicated that, that so, so I haven't, I haven't explained it as as much as I've explained a bunch of other things. And I have to say, I think I think I may be missing a couple of pieces of that argument that uh, would be so. So it's kind of like, well, </s><s>[INST] you're you're conscious being is competition, sha li bounded. So you're missing having written quite a few articles yourself, you you're now missing some of the pieces [/INST] limited </s><s>[INST] being human, [/INST] right? One of the consequences of this, why the why the universe exists thing. And this kind of concept of ruling ads and, and uh, you know, places in there representing our perception of the universe and so on. One of the weird consequences is if the universe exists, mathematics must also exist. And that's a weird thing because mathematics people have been very confused, including me have been very confused about the question of of kind of what, what is the foundation of mathematics? What is what kind of a thing is mathematics? Is mathematics something where we just write down axioms like Euclid did for geometry, and we just build the structure and we could have written down different axioms and we'd have a different structure, Or is it something that has a more fundamental sort of truth to it? And I have to say, is one of those cases where I've I've long believed that mathematics has a great deal of arbitrariness to it, that there are particular axioms that kind of got written down by the babylonians, and that's what we've ended up with the mathematics that we have. And I have to say, actually, my my wife has been telling me for 25 years, she was a mathematician, she's been telling me you're wrong about the foundations of mathematics. And you know, I'm like, no, no, no, I know what I'm talking about. And finally, she's much more right than than I've been. So, it's uh so, </s>
<s>[INST] Well, it's definitely a, a system that could do a lot better and there's a lot of incredible, brilliant people doing science. They deserve better, the better platforms. Uh, so another thing you're taking on helping out with this new limit, which is looking at longevity. What's, what's the idea there? Yeah, [/INST] okay, so as you can see, I'm excited about science, like I think you know science is sort of the basically if you get scientific innovation then you get better products and you get better economic growth and then you get all kinds of like surplus in society that can go to arts and philosophy and like all kind of stuff but um with new limits. So yeah, I I kind of got started hosting some dinners with scientists um last year and I was learning about all kinds of the latest stuff happening in bio and there's a lot of really cool stuff happening with like car t cells and crisper and all these things and um anyway, one of the topics that I started to learn more about was something called cell reprogramming And you know, people maybe have heard of this um-induced pluripotent stem cells where you could take like a skin cell and turn it back into a stem cell and um Shinya Yamanaka won the Nobel Prize for this um work that was done in 2006 and um you know, it's kind of a crazy thing, you can turn one cell into another another type of cell. Well, people recently have been experimenting with um different types of transcription factors that would either not, you don't want to sell to go all the way back to being a stem cell um you can end up getting like cancerous cells and things like that but you wanted basically to, the cell to revert a little bit earlier in its, you know, they would call it the Washington landscape but it's basically like um go become act start to act like a bit of a younger sell but not to differentiate and become more like a stem cell. And so I decided this might be an interesting area to go fund. I think that that team has come together. There's like some really talented people who have come together to help get that off the ground and they're basically building a platform that can test a lot of different transcription factors on different cell types and hopefully find ways to rejuvenate different types of cells and tissues to extend human health span. I mean the Moonshot goal here, you know, they get to mars is um that there could be some therapy here that in I don't know 10 or 20 years that you've taken from a whole body point of view um is sort of rejuvenating tissue, not just one type of tissue like your immune system, but eventually your whole body maybe even your brain so that, you know, we don't have that issue where people who are older have trouble learning or they're more ossified in their thinking um to me this is just I always think about, you know, it's it's actually little inspired by Ellen right, is like what are some of the biggest things in the world like that are probably high technology risk. But if they did work, maybe they're, they're kind of low chance of working. But if they did work would have enormous impact. I like the idea of trying hard tech problems, especially for people like founders like me who have made some money in software, which I think we're in kind of like a golden age of software. So there's like fortunes to be made. But if you, if you do make some money in that, my hope is that people will like, do adam's not bits, you know, and and try some of the harder things like in biotech or um, you know, I guess he's doing cars and rockets and stuff. But anyway, I think we should try hard, hard tech, you know, physical science problems as well and see if that can advance for team human. </s><s>[INST] Yeah. So he's also doing bio with neuralink and I feel like bio is tough because it's messy. [/INST] We </s><s>[INST] don't understand the risk is higher in terms of, uh, not the risk is higher, but like you have to deal with the actual sort of to get to human to get to, to stuff where it could be therapies for actual human bodies. Um, is tricky because you have to prove that it's safe. It's effective, all those kinds of things with, with FDA. I mean, it's just, it's tricky. It's very difficult. It's a long, it's a long journey. I mean if [/INST] I can give a quick, um plug. So yeah, I'm on the board at new limit. We're hiring talented scientists that are interested in the cell reprogramming space. They don't necessarily have to be coming from like an aging background or anything like that. There's sort of a small group people doing even this </s><s>[INST] is a new thing. This is a new limit, relatively new. [/INST] Yeah, it's very new. There's um there's a small team today, just a handful of people. And so we're hiring more there. Um if people are excited about that space, reach out and um same thing for research hub, there's a small team there. That's really awesome. That's doing more like software engineering, design, product, um that kind of stuff. </s><s>[INST] What advice would you give you put on your old wise sage hat, what advice would you give to young people today? High school, Maybe undergrad in college about life. So like career, having a career they can be proud of or maybe a life they can be proud of, [/INST] so people can do whatever they want to be happy, right? So there's not one way to do it. I do think that some people, a particular type of people out there, a lot of people actually, they want to have an impact in the world. That's how they get a sense of fulfillment, right? So I mean you need to have like health, physical, health, you need to have good relationships, like there's lots of things, but most people want to do something important, they want to have fulfilling work a way that they can feel like they're contributing. I think a lot of people, young people today are, are thinking like um you know, I should be an activist or something like that and there's people in the world who have power and I, and I don't, a lot of people don't, I don't have power. And so the way to change the world is to, you know, um speak truth to power or like criticize power and um try to pressure them to change to me. I don't think that's the right way to actually have an impact on the world because um you know, everybody has probably, I think people have more power than they than they realize. Um and by the way, it's easy to be a critic. It's hard to actually change these things and fix it. And so um you'll get a lot of accolades from friends and things like that if you kind of go around criticizing, you know, it's easy to do, like everything is broken and could be better. Um including, you know, stuff I'm working on. I I find like so frustrating a million things I want to be better about like what we're doing coin base. Um so be be the person in the arena, you know like that Theodore Roosevelt quote, I think he said it right? Like go chew glass and stare into the abyss. Like if you really want to have an impact, either join a company that has a mission that is trying to fix the thing you're passionate about or start start that company if it doesn't exist or start a charity, if if it's not suitable to be a company or whatever it is, but go try to be a part of the solution, don't just, you know, criticize or be a part of the problem. My hope is that um more people can, you know, um, realize that they actually can have a meaningful impact that way. And I think that to me, technology is actually one of the most important ways to improve the world. Like if if you look at um climate change, like a lot of the best ideas like carbon sequestration, all these things. It's it's a technology thing, right? If you want to try to fix education, it's like, look at like Khan academy and all the stuff going online. Like if you wanna, if you want to fix um you know, whatever transportation and like um the financial system and global freedom and like equality of all these things. Like there's typically the way to get something changed in the world today is with technology and so I do think people, it's very bizarre to me that there's this kind of like anti tech thing going on. Um look, no, nothing is perfect. Like if you create something new and like tens of millions of people use it or billion people use it, it's like there's gonna be some bad people who use it to okay, and there's, you know, society is complicated, but like, I think most of these things have been net positive because most people in the world are good is at least my view. So yes, we can mitigate like the 1% of bad people trying to, you know, abuse something. But 99% of people in the world are good. And the way you can improve the world is with technology joining companies, starting companies that are working on the right stuff. So I hope, I hope more young people do that. And uh just if you're not sure what to do, like just get started with anything that's how you learn </s>
<s>[INST] So one of the things that you're working [/INST] on, I'm sure there's others working on it, but I don't hear often uh </s><s>[INST] it talked about especially in the clarity that you talk about it and I think it's both the most exciting and the most concerning area of ai in terms of decision making. So you've talked about Ai systems that help make decisions that scale in a distributed way, millions, billions decisions, a sort of markets of decisions. Can you as a starting point? Give an example of a system that you think about when you're thinking about these kinds of systems. [/INST] Uh Yeah, so first of all, you're you're absolutely getting into some territory which will I will be beyond my expertise and and there are lots of things that are going to be very not obvious to think about just like Just uh again, I like to think about history little bit but think about put yourself back in the 60s, there was kind of a banking system that wasn't computerized really. There was there was database theory emerging and database people had to think about how do I actually not just moved it around, but actual money and have it be, you know valid and have transactions at ATMs happen that are actually, you know, all valid and so and so forth. So that's the kind of issues you get into it, you start to get serious about sort of things like this. Um, I like to think about is kind of almost a thought experiment to help me think uh something simpler which is a music market and uh because there is uh the first door, there is no music market in the world right now in the, in our country for sure. Uh there are something called things called record companies and they make money uh and they prop up a few um really good musicians and make them superstars and they all make huge amounts of money. Um, but there's a long tail of huge numbers of people that make lots and lots of really good music that has actually listened to by more people than the famous people. Um um uh, they are not in a market, they cannot have a career, they do not make money. </s><s>[INST] The creators [/INST] creators, the so called influencers or whatever that diminishes who they are, right? So there are people who make extremely good music, especially in the hip hop or latin world these days. Uh they do it on their laptop, that's what they do um on the weekend. Uh and they have another job during the week. They put it up on Soundcloud or other sites, eventually it gets streamed, it gets turned into bits. It's not economically valuable that the information is lost. It gets put up there. People streamed. You walk around in a big city, you see people with headphones on, you know, especially young kids listen to music all the time. If you look at the data, none of them very little of the music they listen to. It is the famous people's music and none of its old music. It's all the latest stuff. But the people who made that latest stuff for like some 16 year old somewhere who will never make a career out of this, who will never make money. Of course, there will be a few counter examples. The record companies incentivized to pick out a few and highlight them. Long story short, there's a missing market there. There is not a consumer producer relationship at the level of the actual creative acts. Um, the pipelines and Spotify, Eyes of the world that take this stuff and stream it along. They make money off of subscriptions or advertising and those things, they're making the money all right. And then they will offer bits and pieces of it to a few people again, to highlight that, you know, they're the simulator market anyway. Real market would be if you're a creator of music that you actually are, Somebody who's good enough that people want to listen to you. You should have the data available to you. There should be a dashboard showing a map of the United States. So in last week here's all the places your songs we listened to, it should be transparent Um vegetable. So that if someone and down in providence sees that you're being listened to 10,000 times in providence that they know that's real data. You know, it's real data. They will have you come give a show down there, they will broadcast to the people have been listening to you that you're coming. If you do this right, you could, you could, you know, go down there make $20,000, you do that three times a year, you start to a career. So in this sense ai creates jobs. It's not about taking human jobs. It's creating new jobs because it creates a new market. Once you've created a market, you've not connected up producers and consumers, you know, the person who's making the music and say to someone who comes to their shows about, Hey, I'll cut your daughter's wedding for $10,000. You'll say 8000, they'll say 9000. Um then you again, you, you can now get an income up to $100,000. You're not going to be a millionaire. All right. And and now even think about really the value of music is in these personal connections even so much so that um a young kid wants to wear a T shirt with their favorite musicians signature on it, right? So if they listen to the music on the internet, the internet should be able to provide them with a button as they push and the merchandise arrives the next day we can do that right now. Why should we do that? Well, because the kid who bought the shirt will be happy, but more the person who made the music, we'll get the money, there's no advertising needed, right? So you can create markets in prison, consumers take 5% cut. Your company will be perfectly uh sound, it will go forward into the future and it will create new markets and that raises human happiness. Um, now this seems like it was easy just create this dashboard kind of creates some connections and all that. But you know, if you think about Uber or whatever, you think about the challenges in the real world of doing things like this and they're actually, new principal is going to be needed. You're trying to create a new kind of two way market at a different scale that's ever been done before. There's going to be uh, you know, uh, unwanted aspects of the market. They'll be bad people, they'll be, you know, um, the data will get used in the wrong ways. You know, it will fail in some ways, it won't deliver value. You have to think that through just like anyone who ran a big auction or you know, ran a big matching service and economics will think these things through. And so that maybe didn't get all the huge issues that can arise. We start to create markets but it starts for at least for me, solidify my thoughts and allow me to move forward in my own thinking. </s>
<s>[INST] is the whole thing. Still differentiate bull? [/INST] Uh No, it's not, it's not trained using backdrop. </s><s>[INST] Okay, that's really important. So uh so there's these feed forward, there's feedback mechanisms. There's some interesting connectivity things is still layered, like uh multiple multiple layers. Okay. Very, very interesting. Uh And yeah, okay, so the interconnection between um adjacent the connections across service constraints that they keep the thing stable. Okay, so what [/INST] else? Uh and then there's this idea of doing inference and neural network does not do in France on the fly. So an example of why this influence is important is, you know, so one of the first applications that we showed in the paper was to crack uh express captures what captures by the way, </s><s>[INST] by the way, one of the most awesome, like people don't use this term anymore human computation. I think I love this term. The guy who created captures, I think came up with this term. Yeah, I love it. Anyway, uh what water [/INST] captures so captures our those strings that you fill in when you're you know, if you're opening a new account in google they show you a picture. You know usually it used to be set of garbled letters that you have to kind of figure out what what is that stink of characters and type it. And the recent captures exist is because you know google or twitter do not want automatic creation of accounts. You can use a computer to create millions of accounts and use that for in nefarious purposes. Uh So you want to make sure that to the extent possible the interaction that their system is having is with a human. So it's a it's called a human interaction proof, capture is a human interaction proof. So so this is it captures that by design things that are easy for humans to solve but hard for computer, hard for robots. Yeah, so and text based captures was the one which is prevalent and around 2014 because at that time text based MS captures were hard for computers to crack. Even now they are actually in the sense of an arbitrary, it expects capture will be unsolvable even now. But with the techniques that we have developed it can be you know, you can quickly developed a handsome that solved the capture. </s><s>[INST] They probably gotten a lot harder to people that they have been getting clever and clever generating these text captures. [/INST] Yeah. So </s><s>[INST] Okay so that was one of the things you've tested it on is these kinds of captures in 2014, 15, that [/INST] kind of stuff. </s><s>[INST] So what uh I mean by the way, why [/INST] captures Yeah, even now, I would say capture is a very, very good challenge problem. Uh if you want to understand how human perception works and if you want to build systems that work like the human brain, uh and I wouldn't say capture is a solved problem, we have cracked the fundamental difference of captures, but it is not solved in the way that humans solved. Um so I can give an example, I can um take a five year old child who has just learned characters, uh show them any new capture that we create, they will be able to solve it. Uh I can show you pretty much any new capture from any new website, You'll be able to solve it without getting any training examples from that particular style of capture, you're assuming I'm human. Yeah, yeah, that's right. So if you're human, if you otherwise I will be able to figure that out using this one. But this </s><s>[INST] whole podcast is just a touring test. That's a long touring test, any website. So, yeah, so she's human, humans can figure it out with very few examples [/INST] or no training examples, no training examples from that particular style of capture. And so you can, you know, so even now this is unreachable for the current deep learning system. So basically there is no, I don't think a system exists where you can basically say train on whatever you want and then now say, hey, I will show you a new capture, which I did not show you in, in the, in the training set up, will the system be able to solve it? Uh still doesn't exist. So that is the magic of human perception and doug have starter put this very beautifully in one office talks the central problem in Ai is what is the letter A If you can, if you can build a system that reliably can detect all the variations of the letter A. You don't even need to go to the V. And you don't even need to go to the VM to see or the strings of characters and uh so that that is a spirit at which you know, with which we tackle that problem, </s><s>[INST] what does it mean by that, I mean, is it uh like without training examples, try to figure out the fundamental elements that make up the letter hey, in all of its forms, [/INST] in all of its forms, it can be, can be made with two human standing leaning against its they're holding the hands. Yeah, uh can be made of leaves, it can be yeah, you </s><s>[INST] might have to understand everything about this world in order to understand the letter A. Yeah, it's common sense reasoning essentially. [/INST] Yeah. So so to finally, to really solve finally to say that we have sold capture, uh you have to solve the whole problem, </s><s>[INST] Yeah. Ok, so how does this kind of the RCN architecture help us to get to do a better job, [/INST] that kind of thing? So as I mentioned, one of the important things was being able to do inference. Being able to dynamically do in France. </s>
<s>[INST] Um That's interesting because I think there's similar like that kind of analysis is so awesome because I think with tennis that have like uh like a fault like when you serve they have analysis of like are you most likely to miss the second serve if you missed the first obviously. Um yeah, I think that's the case, so that integrates, that's so cool when psychology is converted into metrics in that way and in sports it's especially cool because it's such a constraint system that you can really study human psychology because it's repeated, it's constrained so many things are controlled, which is something you rarely have in uh in the wild psychological experiments, so it's cool. Uh plus everyone loves it, like sports is really cool to analyze, [/INST] people actually care about the results. </s><s>[INST] Yeah, I still think well like I will definitely publish this work on messi vs. Ronaldo [/INST] and objective, fully objective to peer </s><s>[INST] review. Uh Yeah, this is very true, this is not passed payer review. Um let me ask sort of uh advice question to uh the young folks, you've explored a lot of fascinating ideas in your life, you built a startup, worked on physics, worked in computer science. What advice would you give to young people today in high school? Maybe early college about life about career, about science and mathematics. [/INST] I remember like uh I read like I remember reading that um punk area was once asked by a french journal about his advice for young people and what was his teaching philosophy and they said that one of the most important things that parents should teach their kids is how to be enthusiastic um in regards to like the mysteries of the world and that he said like striking that balance was actually one of the most important things between like in education you know you want to have your kids be enthusiastic about the mysteries of the world but you also don't want to traumatize them. Like if you really force them into something and I think like especially if you're young, I think it should be curious and I think you should explore that curiosity to the fullest to the point where you even become almost as an expert on that topic and now and you might start with something that it's small. Like you might start with you know you're interested in numbers and how to factor numbers into primes and then all of a sudden you go and you're like lost in number theory and you discover cryptography and then all of a sudden you're buying Bitcoin and I think you should do these um you should really try to fulfill this curiosity and you should live in a society that allows you to fulfill this curiosity which is also important and I think you should do this not to get to some sort of status or fame or money but I think this is the way this iterative process. I think this is the way to find happiness and and I think this is also allows you to find the meaning for your life. I think it's all about like being curious and being able to fulfill their curiosity and that path to fulfilling that your curiosity. </s><s>[INST] Yeah, the start small and not the fire build is kind of interesting way to think about [/INST] it and you never know where you're going to end up, it's like, firmas is just a really good example. We started like by doing this as an internal like thing that we did in the company and then we started putting out there and now a lot of people follow it and know about it and so, um </s><s>[INST] and you still don't know where from our library is going to end up actually [/INST] True. Exactly, so um yeah, I think that would be my piece of advice with very limited experience of course, but yeah, yeah, I agree, I agree. </s><s>[INST] I mean, is there something in from particular as you all from the computer science physics perspective? Uh do do you regret not doing physics? Do you regret not doing computer science? Which one is the wiser, the better human being, This is messy versus Ronaldo. Um uh those are very, I don't know if you would agree, but they're kind of different disciplines. [/INST] True. Yeah, very much so. Um actually, I actually, uh I was, I had that question in my mind, I, I took physics classes as an undergrad or like, besides what I had to take and it's definitely something that I considered at some point. Um and and that, that I do feel like later in life that might be something that I'm not sure if regret is is the right word, but it's it's kind of something that I can imagine in an alternative universe, what would have happened if I if I had gone into physics? Um I try to think that like, well it depends on what you're path ends up being, but that it's not super important right? Like exactly what you decide to major on, like I think there's there's um I think tim urban, like the blogger has a good visualization of this, where it's like, you know, like he has a picture where you have all sorts of paths that you could pursue in your life and then maybe you're in the middle of it and so there's maybe some paths that are not accessible to you, but like the tree that is still in front of you gives you a lot of optionality. And so um </s>
<s>[INST] So let me ask about knowing yourself. This is fun. This is fun, quick questions about day in the life, The perfect day, the perfect productive day in the life of Dennis's house. Maybe uh maybe these days your there's a lot involved. So maybe slightly younger nemesis when you could focus on a single project maybe. Um How early do you wake up? Are you night owl? Do you wake up early in the morning? What are some interesting habits, How many dozens of cups of coffee do you drink a day? What's the computer um that you use? What's the setup? How many screens, what kind of keyboard we're talking imax vim or we're talking something more modern? A bunch of those questions. So maybe a day in the life, what what's the perfect day involved? [/INST] Well, these days it's quite different from say 10, 20 years ago, back, 10, 20 years ago, it would have been, you know, a whole day of research, individual research or programming, doing some experiment, neuroscience, computer science experiment, reading lots of research papers. Uh and then perhaps at nighttime, you know um reading science fiction books or or playing some games, </s><s>[INST] but lots of focus. So like deep focused work on whether it's uh programming or reading research papers. Yes, [/INST] So that would be a lot of deep, you know, focus work these days for the last sort of I guess, you know, 5 to 10 years, I've actually got quite a structure that works very well for me now, which is that I'm a night complete night owl always have been. So I optimize for that. So, you know, I get, you know, I basically do a normal day's work, get into work about 11 o'clock and sort of do work to about seven in the office. Uh And I will arrange back to back meetings for the entire time of that and with as many meet as many people as possible. So that's my collaboration management part of the day. Then I go home spend time with the family and friends, have dinner, relax a little bit and then I start a second day of work. I call it my second day of work around 10 p.m. 11 P. M. And that's the time till about the small hours of the morning, 45 in the morning where I will do my thinking and reading a research, writing research papers. Um sadly I don't have time to code anymore, but it's it's not efficient to do that these days given the amount of time I have. Um But that's when I do, you know maybe do the long kind of stretches of of thinking and planning and then probably, you know, using using email, other things. I would set, I would fire off a lot of things to my teams to to deal with the next morning for actually thinking about this overnight, we should go for this project or arrange this meeting the next day. </s><s>[INST] When you think through a problem, you're talking about a sheet of paper or is there some structure? [/INST] I still like pencil and paper best for working out things, but these days it's just so efficient to read research papers just on the screen. I still often print them out actually. I still prefer to mark out things and I find it goes into the brain quick better and sticks in the brain better when you're you're you're still using physical pen and pencil and paper. </s><s>[INST] So you take notes. I [/INST] have lots of notes, electronic ones and also whole stacks of notebooks that that that I use at home. Yeah. </s><s>[INST] Some of these most challenging next steps, for example stuff. None of us know about that. You're working on your thinking there's some deep thinking required there, right? Like what what is the right problem? What is the right approach? Because there you're gonna have to invest a huge amount of time for the whole team. They're going to have to pursue this thing. What's the right way to do? It is RL gonna work here or not. Um What's the right thing to try, what's the right benchmark to you. We need to construct the benchmark from scratch all those kinds of things. [/INST] So I think of all those kind of things in the night time phase but also much more. I find I've always found the quiet hours of the morning um when everyone's asleep it's super quiet outside. Um I love that time, the golden hours like between like one and three in the morning. Um Put some music on, some inspiring music on and then I think these deep thoughts. So that's when I would read you know my philosophy books and Spinoza, my you know recent favorite can all these things I read about a great a scientist of history, how they did things, how they thought things. So that's when you do all your create, that's when I do all my creative thinking and it's good I think I think people recommend, you know you do your your your sort of creative thinking in one block and the way I organize the day that way I don't get interrupted because obviously no one else is up at those times. So I can I can go you know as I can sort of get super deep and super into flow. The other nice thing about doing it night time wise is if I'm really onto something or I've got really deep into something I can choose to extend it and I'll go into six in the morning whatever and then I'll just pay for it the next day. I'll be a bit tired and I won't be my best, but that's fine. I can decide looking at my schedule the next day and given where I'm at with this particular thought or creative idea that I'm going to pay that cost the next day. So, so I think that's that's more flexible than morning. People who do that. You know, they get up at four in the morning, they can also do those golden hours then, but then their start of their scheduled day starts at breakfast, you know, am whatever they have their first meeting. And then it's hard you have to reschedule a day if you're in flow. Yeah, </s>
<s>[INST] Yeah, that's that's not often talked about is the scale of the data said it was trained on and the quality of the data set because there's [/INST] some </s><s>[INST] uh it was like reddit threads that had they were operated highly. So there's already some weak supervision on a very large data set that people don't often talk about right. [/INST] I find it today we have maturing processes to managing code. Things like get right version control talked a long time to evolve the good processes. I remember I remember when my friends and I were emailing each other C Plus was files and email, you know, but then we had was that CVS subversion get maybe something else in the future. Um We're very immature in terms of two. So managing data and think about the clean data and how to solve a very hot messy data problems. I think there's a lot of innovation there to be had. Still </s><s>[INST] I love the idea that you were versioning through email. [/INST] I'll give you one example when we work with uh manufacturing companies um is not at all uncommon for there to be multiple labelers that disagree with each other. Right? And so we would um doing the work in visual inspection. We will, you know, take a plastic part and show to one inspector and the inspector sometimes very opinionated. They'll go clearly that's a defect. The scratch on the set to go to reject this pot. Take the same part. Two different inspector. Different very often it's clearly the scratches small, it's fine. Don't throw it away, you're gonna make us use. And then sometimes you take the same plastic part. Show to the same inspector in the afternoon I suppose in the morning and very fanatical in the morning. They said clearly it's okay in the afternoon, equally confident. Clearly this is a defect. And so what is the I team's supposed to do if if sometimes even one person doesn't agree with himself or herself in the span of a day. So I think these are the types of very practical, very messy data problems that that that you know that my team's wrestle with. Um in the case of large consumer internet companies, we have a billion users. You have a lot of data, you don't worry about it. Just take the average, it kind of works. But in the case of other industry settings, we don't have big data is just a small data. Very small data says maybe in 100 defective parts um or 100 examples of a defect. If you have only 100 examples, these little labeling service, if 10 of your 100 labels are wrong, That actually is 10% of it is that has a big impact. So how do you clean this up? What you're supposed to do? This is an example of the types of things that um my team, this is a landing ai example are wrestling with to deal with small data, which comes up all the time once you're outside consumer internet. </s><s>[INST] Yeah, that's fascinating. So then you invest more effort and time and thinking about the actual labeling process. What are the labels, what are the Hollywood disagreements resolved and all those kinds of like pragmatic real world problems. That's a fascinating space. [/INST] Yeah, I find it actually when I'm teaching at Standard, I increasingly encourage students that standard to um try to find their own project for the end of term project rather than just downloading someone else's nicely clean dataset. It's actually much harder if you want to go and to find your own problem and find your own dataset rather than you go to one of the several good websites. Very good websites with with clean scoped data sets that you could just work on. </s><s>[INST] You're not running three efforts that Ai fund landing AI and deep learning dot Ai, as you've said that AI fund is involved in creating new companies from scratch landing Ai is involved in helping already established companies do AI. And deep learning AI is for education of everyone else or of individuals interested of getting into the field and excelling in it. So let's perhaps talk about each of these areas first. Deep learning dot Ai. How the basic question, how does a person interested in deep learning get started in the field? [/INST] The AI is working to create causes to help people break into A. I so uh my machine learning course that I talked to stanford means one of the most popular courses on coursera </s><s>[INST] to this day. It's probably one of the courses sort of if I asked somebody, how did you get into machine learning or how did you fall in love with machine learning or get you interested. It always goes back to and rang at some point, you have influence the amount of people you influence is ridiculous. So for that. I'm sure I speak for a lot of people say a big thank you. [/INST] Yeah, thank you. You know, I was once reading a news article um uh I think it was tech review and I'm gonna mess up the statistic. But I remember reading an article that said um something like one third of our programmers are self taught, I may have the number one, third round was two thirds. But when I read that article, I thought this doesn't make sense. Everyone is self taught because you teach yourself, I don't teach </s><s>[INST] people, I just don't get it now. So yeah, so how how does one get started in deep learning and what is deep learning dot ai fit into that? [/INST] So the deep specialization offered by deviant Ai is uh I think uh it was called Sarah's specialization. It might still be. So it's a very popular way for people to take that specialization to learn about everything from your networks to how to tune in your network. So what is the confident to what is a R N N or sequence model or what is an attention model? And so did the specialization um steps everyone through those algorithms. So you deeply understand it and can implement it and use it for whatever from </s>
<s>[INST] And and what was the finding people? I guess it's also like finding the right kind of customer [/INST] The right kind of client. I got like in a lot of trouble for this recently in the sex worker sphere because I said that if You raise prices you're more likely to encounter clients that aren't going to abuse you Like it's safer. Yeah, they did not they Said that I was being classist, you know implying that poor people are more violent But to be fair if you're a guy and you want to be violent towards a woman You're probably not gonna be paying her a lot of money You're probably gonna like you're the kind of person likely who's going to haggle a lot because you don't respect her But anyway that aside it's a little pet peeve for me Yeah, I just I charged started charging 800 an hour and then pretty rapidly raised it to 1200 and then a while after that </s><s>[INST] Raise it to 1400. Well, the interesting thing you mentioned in my extensive research You used to do 1200 to 1400 an hour and then you said that you're thinking of jumping back in at a rate of 2400 the first hour Yeah, and I think 900 each successful hour. That's interesting [/INST] That's like that's that I mean it to me. That's really interesting like the first like why it's like like Why's the first hour? Yeah a lot of the first hour. Oh, yeah, oh it's just because Just depends on how you want to incentivise like the amount of hours so you have to pay a lot for the first hour but not very much for this excessive you're more likely to buy like a Longer period of time and usually, I find that clients who buy a longer period of time are nicer to you I don't care like a great theory for why that is but there's the more likely like you did and get to know You first and I just enjoy that a lot more. I enjoy like Like no, I'm gonna have sex with </s><s>[INST] Like a date, you know? Yeah, so it incentivized the long form date dynamic versus like a knot. That's really interesting. That's really interesting. How does money change the dynamic? Just basic human dynamic of interacting for free versus for money. Like I think about that a lot because like just talking to rich people, it's like you usually get paid for your time and you're doing this for free. Like what's the difference? [/INST] Is there a difference really or no? Yeah, so I've actually, it depends a lot. So when I was doing it full time, it was my only source of income. It changed quite a lot because I was really incentivized to have repeat customers. So I'm like, okay, if I'm, my primary interaction with you is to like have you hire me again. I will do whatever that takes to make that happen. And so if I have to like laugh at jokes that I don't find funny or like be like more adoring of your penis than I actually genuinely feel, like that's what I'm going to express. And obviously it's to some degree like titrated, you know, like it's unpleasant to force yourself to like something that you don't. So like I would actually like not see clients again that I didn't want to, but it's just some degree there was a sort of self-suppression going on, which I think is the way it works in any sort of customer service job. Like you want the customer to leave happy. So you just make sure that you are happy the whole time and you're like, ah, really enjoying the other person. But so recently when I've like kind of dabbled in it since baking money through other means where I don't need the money, it's more like a fun side thing that I'm, like I said, it's fulfilling the role of casual sex for me. So like, I don't have to do it. This is not my primary job. I just want sort of a good excuse to like have sex with somebody and the money is like a great filter for that. </s><s>[INST] And so in that case. That's interesting. So the money is, but yeah, okay, the money is basically a filter for somebody [/INST] who's taking this interaction seriously. Yeah, it also, so there's an interesting like psychological thing where I have difficulty having casual sex with somebody because some part of my brain, which I assume is like quite female, is doing some evaluation of status whether or not this is going to damage my reputation by having sex with them. If you found out that I went and had random sex with a homeless man, you might be like, wow, that says something about Ayla. Maybe she's trashy or she just has no standards for who she's going to fuck. Some part of me is continually anxious. I'm like, does this mean I have no standards if I decide to have casual sex with you? What are people going to think? If you introduce money, it takes away that anxiety. I don't have to worry about it because it's like, oh, of course Ayla would have sex with that person. They paid her. She's the person of the kind of mate that she can get. This is just an indication of a business transaction. This allows me to enjoy casual sex so much more when somebody pays me for it to the degree that I almost view it as a kink. I'm using it to replace casual sex and occasionally I'm like, just pay me a little bit to erase the anxiety and I'll have a fun time. </s>
<s>[INST] Know the feeling is the number of programmers in the world has been growing and growing very quickly. Do you think it's possible that it will actually level out and drop to like a very low number with this kind of world? Because then you'll be doing software 2.0 programming. Um And you'll be doing this kind of generation of co pilot type systems, programming but you won't be doing the old school software one point oh programming. I [/INST] don't currently think that they're just going to replace human programmers. Um I'm so hesitant saying stuff like this right because </s><s>[INST] this is going to be replaced [/INST] in five years. </s><s>[INST] I know it's going to show [/INST] that like this </s><s>[INST] is where we thought because I I agree with you but I think we might be very [/INST] surprised </s><s>[INST] right? Like what are the next i what's your sense of where we stand with language models? Like does it feel like the beginning or the middle or the end? [/INST] The beginning? 100%. I think the big question in my mind is for sure. GPT will be able to program quite well competently and so on. How do you steer the system? You still have to provide some guidance to what you actually are looking for. And so how do you steer it? And how do you say, how do you talk to it? How do you um audited and verified that what is done is correct. And how do you like work with this? And it's as much not just an ai problem but a ui ux problem. Yeah. Um So beautiful fertile ground for so much interesting work for V. S. Code plus plus where you're not just not just human programming anymore. It's amazing. </s><s>[INST] Yeah. So you're interacting with the system so not just one prompt but its iterative prompting trying to figure out having a conversation with the system. That actually I mean to me that's super exciting to have a conversation with the program I'm writing. [/INST] Yeah maybe at some point you're just conversing with it. It's like okay here's what I wanna do actually this variable. Maybe it's not even that low level is variable but you </s><s>[INST] can also imagine like can you translate this to C. Plus plus and back to python [/INST] already kind of existence </s><s>[INST] but just like doing it as part of the program experience. Like I think I'd like to write this function in C Plus plus or like you just keep changing from different different programs because there's different syntax, maybe I want to convert this into a functional language and so like you get to become multi lingual as a programmer and dance back and forth officially. [/INST] I think the Ui ux of it though is like still very hard to think through because it's not just about writing code on a page, you have an entire developer environment, you have a bunch of hardware on it. Uh you have some environmental variables, you have some scripts that are running in a Cron job like there's a lot going on to like working with computers and how do these systems set up environment flags and work across multiple machines and set up screen sessions and automate different processes like how all that works and is auditable by humans and so on is like massive questions. The moment </s><s>[INST] you've built archive sanity, what is archive and what is the future of academic research publishing that you would like to see? [/INST] So archive is this pre print server. So if you have a paper you can submit it for publication to journals or conferences and then wait six months and then maybe get a decision pass or fail or you can just uploaded to archive and then people can tweet about it three minutes later and then everyone sees it. Everyone reads it and everyone can profit from it in their own ways </s><s>[INST] and you can cite it and it has an official look to it. It feels like a like it feels like a publication process. It feels different than if you just put in a blog post. [/INST] Oh yeah, I mean it's a paper and usually the bar is higher for something that you would expect on archive as opposed to and something you would see in a blog post </s><s>[INST] or the culture created the bar because you could probably host a pretty crappy fix for an archive. Um So what's that make you feel like, what does that make you feel about peer review? So rigorous peer review by 23 experts versus the peer review of the community? Right? As it's written [/INST] basically, I think the community is very well able to peer review things very quickly on twitter and I think maybe it just has to do something with A. I. Machine learning field specifically though, I feel like things are more easily auditable. Um and the verification is easier potentially than the verification somewhere else. So it's kind of like um you can think of these scientific publications as like little block chains where everyone's building on each other's work and setting each other and you sort of have A I which is kind of like this much faster and loose Blockchain, but then you have, and any one individual entry is like very, very cheap to make and then you have other fields where maybe that model doesn't make as much sense. Um And so I think in a I at least things are pretty easily verifiable and so that's why when people upload papers, they're a really good idea and so on, People can try it out the next day and they can be the final arbiter of whether it works or not on their problem and the whole thing just moves significantly faster. So I kind of feel like academia still has a place, sort of just like conference journal process still has a place, but it's sort of like um it lags behind I think and it's a bit more maybe higher quality process, but it's not sort of the place where you will discover cutting edge work anymore. It used to be the case when I was starting my PhD that you go to conferences and journals and you discuss all the latest research now when you go to a conference or general like no one discusses anything that's there because its already like three generations ago irrelevant. </s>
<s>[INST] but I still I have that self critical voice. I just after every after this podcast, I'll probably be like, you you're boring, why are you so boring? That that that [/INST] that that </s><s>[INST] and I just gave a lecture at m I T I was like, I got so much love from people, They're such beautiful people. And I just remember walking home just feeling like, like I wasted everybody's time, you know, and it's it's I don't know what that is. I don't you know, I I do hope that that's a voice that won't destroy me. You know, like, [/INST] I that's really human of you to admit that, because people don't wanna they wouldn't assume that of course from you or anything that I mean, you've got a large group of students in there listening to you and feeling the way and thinking what they think of you. Uh so that's really interesting to hear you um admit that, but it's also I would expect nothing else You have to be able to such a, I mean you're a human being </s><s>[INST] and I'm trying to figure out if that, you know, some people that might hear that, they would say, well that's a problem you have to fix. And I think that that might be just who I am [/INST] because </s><s>[INST] I'm not, you know, I've been very, very fortunate to have chemical, you know, like the depression where I get into a dark place, like it gets stuck in the, in the, in the downward spiral. It's it's usually a thing that last you write it out and you and then after a good night's sleep, you're back to uh back to your happy self. So I think I have to try to figure that out. Is that just part of the creative process being a creative human in this world? I [/INST] haven't found any other way. I'm always kicking myself </s><s>[INST] take that dude. You can't, you can't, you're, you're not gonna be human until you feel some despair, criticism [/INST] absolutely hate the ship that you're doing sometimes. </s><s>[INST] What small act of kindness were you once shown that you will never forget? There's something jumped to mind where somebody just did something that made you smile. Did you feel connected to the rest of humanity? [/INST] Yeah, yeah, lots of things, you know. Um but I remember my niece one time one of my nieces, we were in her neighborhood and she was like, she might have been five or six at the time. They're all adults now. My brother and sister older than me and the kids are all the youngest is 22. And uh yeah, anyway, one of my nieces, she was just she had ice cream, we went out and we got ice cream walking around the neighborhood, her neighborhood. And uh she said something to me that I don't think she understands how much it meant at the time. But she goes she goes, people love you here, you know that and she doesn't know where here is. She's five years old. But she was just looking at the kids playing in the park and the people walking their dogs and everyone just wants people love you here, you know that but she didn't know how much I needed to hear that at that point which is really heavy for me. I'll never forget it. I've never told her that well. And anytime you get a little something from people, especially in a terrier ass out city like L. A. Where somebody has any fucking time for you when someone can slow it down and say something. You know I saw this actor once in my grocery store that I go to who made me laugh so fucking hard in this one movie. And every time I see this clip I still laugh and um I am kind of shy, you know personally. But so he uh he was walking by, he was walking out and I was walking in and I go that's that guy and I did not stop to just let him know how great I thought he was in this film and I always kind of regret it, you know what I mean? So as hard as it is and sometimes I still don't, if I see someone that has done something in, in, you know, in any way it doesn't have to be in show business or anything like that, I try and I try and say hey that's that's really good, you know what I mean? Um because to get that from someone can mean a lot, you </s><s>[INST] know a certain time in life when you need [/INST] it, I </s><s>[INST] can make a big difference. I mean I sorry to uh take it back to my new girlfriend, the waitress. [/INST] Oh yeah, but </s><s>[INST] she, there's something about her saying sweetheart Yeah, I was in a pretty low place for some reason mentally and it's just that the basic human kindness was nice. [/INST] Yeah, yeah, yeah, yeah, I hear you. I was at a restaurant in uh new york recently and I was shooting something and my fiance was able to fly in for a week and uh but she was back at the hotel and it's like I felt like I was cheating on her because there was this nice waitress at this barbecue place I went to and first of all, my fiance would not like me eating any greasy, sugary barbecue. So I felt like I was cheating </s><s>[INST] on delicious food over [/INST] but the waitress was one of these, you know, she was this the kind of server who's like, hey hon you think, hey sweetie, like blah blah blah, but like so chill and at ease in the middle of a part of new york, that's really, you know, kind of fucking pretentious and you know, and everybody but sweet people fucking way better people than we got here. But uh I know that but you know, it's part of new york and whatever I'm there working and people, I'm like, you know, I've been trying to impress one another and, and uh she was just even had some sort of an accent that was not, didn't feel like an atlantic american accent. Uh yeah, although those, yeah servers that say sweetheart and hon that's what we need from ai we need that, that Jetsons server. But </s>
<s>[INST] the benefit of drilling. I'm just playing devil's advocate with. The benefit of drilling is that you can more efficiently get a higher number of reps in. So [/INST] what are you gonna gain with those reps? </s><s>[INST] Understanding the mechanics of the movement? And what I would like to argue is you don't necessarily need the resistance to deeply understand the mechanics or something. [/INST] Now I don't </s><s>[INST] know there's something for there's some moves like I bet you you could drill your way to an incredible mount. Like Mao is a good example of that. You don't really need to visit one. I can imagine a world in which the resisting opponent is not essential for developing some of the very fine details of the mechanics [/INST] of what you say amount. </s><s>[INST] Yes. [/INST] What you're going to achieve by resist by drilling with no resistance. After you learn the mechanics amount. </s><s>[INST] But what I'm trying to tell you the learning the mechanics isn't a thing where you get a certificate and you're done. You're gonna learn the fine details of the way you redistribute your way, you're going to learn how to move your I don't understand [/INST] that that body </s><s>[INST] what like [/INST] everything you do is a slow process and timing. </s><s>[INST] You have to [/INST] understand moving. It's the guys resistant. Like he's not, I'm not gonna grab you and apply the movement. I need to grab you and Phil when is the right time to do like that? That he only comes when you were with movement. If you're not fully resistant, how would I know </s><s>[INST] you couldn't infer through it? It's like uh [/INST] with no movement with no resistance. Like, look you, okay, let's say you've been drilling for a week, five hours a day. You should be an expert with the mechanics. But now how are you going to carry on drilling? No resistance. </s><s>[INST] Exactly after [/INST] that week, drilling five times five hours a day. The arm lock, you still have no clue how to apply the arm lock against a resisting opponent. No clue. Zero. So you don't know the movement. You know the mechanic, which is, you know, it's like how long you have to drill and how that doesn't matter. It's the various of the person you can do for a month after that month is over. You should understand how the mechanic works. You still have no clue how to apply the movement against a resisting opponent. You will never ever know how until you apply with a fully resistant opponent. That's the only way to know to, to to really learn a movement. </s><s>[INST] Yes, well put, but the question is, can you have a small percentage of time when you go against a resisting opponent to get the wisdom and the insight of what it takes to perform that movement. And you spend a large percentage of other time just practicing the mechanics of it. So like uh do you need to as you get better and better a technique to basically drift away completely from drilling and more into the sparring? I'd like to I just [/INST] you like really </s><s>[INST] know, I don't like drilling. I see I well yes, I like drilling I would say. But I just see it always bothered me in the jiu jitsu community how few people really saw the value of drilling. I see the wrestling, especially in the in the Russian style of wrestling, like the value of drilling. I don't necessarily mean that it's like a dead body or like a dummy or something like that. But just getting the reps in really focusing on the high amount of reps. [/INST] I agreed in wrestling and judo, I agree the drilling is very important. Initial drill 1000 times each move </s><s>[INST] judo is a really big one for [/INST] that. It is because is the movement at the time, You know, it is the precision of the movement. It has to be perfectly because it's one movement then is you learn about the timing of the movement when you're fighting, but doing fighting, you only need to know the time because your body movement is exactly the same when you drill </s><s>[INST] the mechanics is much more important there. [/INST] Yeah, but it's completely different for jujitsu because let's say from jiu jitsu like the arm lock for example, we use that as an example. Let's see from the closed guard given my close guard before I go for the arm lock, I need to have a set of grips, let's say I have your call in your arm, right? And then you know when you're drilling, I'm gonna grab your arm, I'm gonna grab your collar and I'm gonna drill my body until I can apply the arm lock and finish. I can do that 1000 times. Okay, now we're fighting, we start with the grip. The moment that I initiate the arm lock attack, you will defend. The arm lock will not work. So it's not the one movement that will get me to attack the arm. There's a there's a combination of other things that I need to do, I need to feel about your weight. You know, I need to get you close to me. There's so many other things involved that I need to feel that only comes with life. Life with a fully resistant opponent. Yeah, </s><s>[INST] so pretty quickly it has to be live [/INST] and then it comes how you practice how you train, it's starting on that position and just saying let's go and and the moment that we disengage from that position, we go back. That's when you really learn because everything that you do wrong, you're gonna go back there and you're gonna try again, try again, try again. And the repetition, it will teach you have a feeling of timing when to go if there's, you know, there's all the combinations which he always has to go with it </s>