Andrej Karpathy

You can look at a lot of animals, like, for example, zebras.

Zebras get born, and they see, and they can run.

There's zero training data in their lifespan.

They can just do that.

So somehow, I have no idea how, evolution has found a way to encode these algorithms and these neural net initializations that are extremely good into ATCGs.

And I have no idea how this works, but apparently it's possible, because here's a proof by existence.

Yeah.

I think it's just like the hardware for long-term memory is just not fully developed.

Sure.

I kind of feel like the first few years of, uh, uh, of infants is not actually like learning.

It's brain maturing.

Yeah.

Um, we're born premature.

Um, there's a theory along those lines because of the birth canal and the swelling of the brain.

And so we're born premature.

And then the first few years were just the brains maturing.

Uh, and then there's some learning eventually.

Um,

That's my current view on it.

Yes, but I don't know to what extent it will be explicitly constructed.