Manolis Kellis

What's unique is that, as I mentioned earlier, every one of us was trained by a different subset of human culture.

And Chachapiti was trained on all of it.

And the difference there is that it probably has the ability to emulate almost every one of us.

The fact that you can figure out where that is in cognitive behavioral space just by a few prompts is pretty impressive.

But the fact that that exists somewhere is absolutely beautiful.

And

The fact that it's encoded in an orthogonal way from the knowledge, I think is also beautiful.

The fact that somehow through this extreme over-parameterization of AI models, it was able to somehow figure out that context, knowledge, and form are separable.

and that you can sort of describe scientific knowledge in a haiku in the form of, I don't know, Shakespeare or something, that tells you something about the decoupling and the decouplability of these types of aspects of human psyche.

So with convolutional neural networks, interpretability,

had many good advances because we can kind of understand them.

There's a structure to them.

There's a locality to them.

And we can kind of understand that different layers have different sort of ranges that they're looking at.

So we can look at activation features and basically see where, you know, where does that correspond to.

With large language models,

It's perhaps a little more complicated, but I think it's still achievable in the sense that we could kind of ask, well, what kind of prompts does this generate?

If I sort of drop out this part of the network, then what happens?

And sort of start getting at a language to even describe these types of aspects of human behavior.

behavioral psychology, if you wish, from the spoken part in the language part.