Dwarkesh Patel

No, of course not.

Really?

Yeah.

I think kids just like watch people.

They like kind of try to like say the same words.

I think the level- What about the first six months?

I think they're kind of imitating things.

They're trying to like make their mouth sound the way they see their mother's mouth sound.

And then they'll say the same words without understanding what they mean.

And as they get older, the complexity of the imitation they do increases.

So you're imitating maybe the skills that your people in your band are using to hunt down the deer or something.

And then you go into the learning from experience RR regime.

But I think there's a lot of imitation learning happening with humans.

uh infant actually does there's no targets for that there are no examples for that I agree that doesn't explain everything infants do but I think it guides the learning process I mean even uh llm when it's trying to predict the next token early in training it will like make a guess it'll be different from what like it actually sees and in some sense it's like very short horizon RL where it's like making this guess of like I think this token will be this it's actually the other thing similar to how a kid will try to say a word it comes out wrong

I think this is maybe more of a semantic distinction.

Like, what do you call school?

Is that not training data?

You're not going to school because it's like... School is much later.

You shouldn't base your theories on that.

But the idea of having phases of learning where... I think you're just sort of programming your biology that early on you're not that useful.