Stephen Wolfram

Yeah, it's also what's happening is one of the things that's, is for example, when there's these messages, there's documentation about these messages, there's examples of where the messages have occurred otherwise.

Nice.

All these kinds of things.

The other thing that's really amusing with this is when it makes a mistake, one of the things that's in our prompt when the code doesn't work is read the documentation.

And we have another piece of the plugin that lets it read documentation.

And that, again, is very, very useful because it will figure out.

Sometimes it'll make up the name of some option for some function that doesn't really exist, read the documentation.

It'll have some wrong structure for the function and so on.

That's a powerful thing.

I mean, the thing that I've realized is

We built this language over the course of all these years to be nice and coherent and consistent and so on, so it's easy for humans to understand.

Turns out there was a side effect that I didn't anticipate, which is it makes it easy for AIs to understand.

Well, yes.

I mean, maybe.

That's an interesting question, because it really depends on what I see as being an important piece of fundamental science that basically just jumped out at us with ChatGPT.

Because I think the real question is, why does ChatGPT work?

How is it possible to encapsulate, to successfully reproduce all these kinds of things in natural language?

with a comparatively small, he says, couple hundred billion weights of neural net and so on.

And I think that relates to kind of a fundamental fact about language, which the main thing is that I think there's a structure to language that we haven't kind of really explored very well.

It's kind of the semantic grammar I'm talking about.