Stephen Wolfram

Right.

The plugin that we have for ChatGPT, it does that routinely.

It will send the thing in.

It will get a result.

It will discover.

The LLM will discover itself that the result is not plausible.

And it will go back and say, oh, I'm sorry.

It's very polite.

And it goes back and says, I'll rewrite that piece of code.

And then it will try it again.

and get the result.

The other thing that's pretty interesting is when you're just running, so one of the new concepts that we have, we invented this whole idea of notebooks back 36 years ago now.

And so now there's the question of sort of how do you combine this idea of notebooks where you have text and code and output

How do you combine that with the notion of chat and so on?

And there's some really interesting things there.

Like, for example, a very typical thing now is we have these notebooks where as soon as the – if the thing produces errors, if they run this code and it produces messages and so on,

the LLM automatically not only looks at those messages, it can also see all kinds of internal information about stack traces and things like this.

And it can then, it does a remarkably good job of guessing what's wrong.

In other words, it's looking at things.

It's sort of interesting.