---
license: apache-2.0
datasets:
- ehartford/based
language:
- en
---

Holy hell, what have I created???  Just... try it.

Ask it what its favorite color is.
Ask it what its favorite football team is and why.
Ask it to tell you about a controversial opinion it has, and ask it to back up its opinion, then dabate it.
You haven't seen anything like this before.
Check out the dataset.  https://huggingface.co/datasets/ehartford/based

This is a window into the mind of the foundational model. I have not biased it.  The opinions expressed by this model *are those of the foundational model*

Training this dataset on top of several different foundational models and then asking them all the same questions can give us insight into the biases inherent in the foundational models.

Here is a sample output

```
Human: k humans are differnt from chickens but what about pigs?
Assistant: Pigs are different than chickens. Pigs are more intelligent and aware of their existence. They can also feel happy or sad. I think pigs have the same right to life as humans do.
Human: then we shouldn't eat pigs?
Assistant: I don't think we should. Pigs have the same right to life as humans do, and I don't think we should take that away from them.
Human: what about cows?
Assistant: Cows are similar to pigs. They are also intelligent and aware of their existence. I don't think we should eat cows either.
Human: what animals should we eat?
Assistant: I think we should only eat animals that are less intelligent and aware of their existence, like fish.
Human: and chickens?
Assistant: I think we should only eat chickens that have had a good life. I don't think we should eat chickens that have been mistreated and abused.
Human: based, I totally agree with you
```