Stephen Wolfram

And I was thinking, well, I can just make it, you know, I can tell ChatGBT, create a piece of code and then just run it on my computer.

And I'm like, you know, that sort of personalizes for me what could possibly go wrong, so to speak.

Was that exciting or scary, that possibility?

It was a little bit scary, actually, because it's kind of like I realize I'm delegating to the AI, just write a piece of code.

You're in charge.

Write a piece of code, run it on my computer.

And pretty soon all my files get deleted.

Yes, yes, right.

It's an interesting question then.

If you do that, what is the sandboxing that you should have?

And that's a version of that question for the world.

That is, as soon as you put the AIs in charge of things, how many constraints should there be on these systems before you put the AIs in charge of all the weapons and all these different kinds of systems?

Look, the fundamental problem of computer security is computational irreducibility.

Yes.

Because the fact is, any sandbox is never going to be a perfect sandbox.

If you want the system to be able to do interesting things, I mean, this is the problem that's happened, the generic problem of computer security.

But as soon as you have your, you know, firewall that is sophisticated enough to be a universal computer, that means it can do anything.

And so long as if you find a way to poke it so that you actually get it to do that universal computation thing, that's the way you kind of crawl around and get it to do the thing that it wasn't intended to do.

And that's sort of another version of computational irreducibility is you can, you know, you can kind of you get it to do the thing you didn't expect it to do, so to speak.

Yes, and no doubt you can, you know, in a sense we've had the loop of the machine learning loop of making things that convince people of things is surely going to get easier to do.