Stephen Wolfram

But it's something where I think that's sort of the deep computation.

It's really what humans can do quickly

large language models will probably be able to do well.

Anything that you can do kind of off the top of your head type thing is good for large language models.

And the things you do off the top of your head, you may not get them always right, but it's thinking it through the same way we do.

Well, the question is, what do you want the code base to do?

Okay.

So the thing is, when people say, we want to build this giant thing, right?

A giant piece of computational language.

In a sense, it's sort of a failure of computational language if the thing you have to build, in other words, if we have a description, if you have a small description,

That's the thing that you represent in computational language, and then the computer can compute from that.

Yes.

So in a sense, as soon as you're giving a description, you have to somehow make that description something definite, something formal.

And to say, okay, I'm going to give this piece of natural language, and then it's going to splurt out this giant formal structure,

That, in a sense, that doesn't really make sense because except insofar as that piece of natural language kind of plugs into what we socially know, so to speak, plugs into kind of our corpus of knowledge, then that's a way we're capturing a piece of that corpus of knowledge, but hopefully we will have done that in computational language.

How do you make it do something that's big?

Well, you have to have a way to describe what you want.

I can make it more explicit if you want.

Right.

If I can describe what I want, to what extent can a large language model automate that?