Sam Altman

You know, that's not very cool.

Do you think GPT-4 is conscious?

How to fake consciousness?

I mean, look, you don't know, obviously, we can go to the freshman year dorm late at Saturday night kind of thing.

You don't know that you're not a GPT-4 rollout in some advanced simulation.

Yeah, yes.

So, if we're willing to go to that level, sure.

Maybe I can just share a few disconnected thoughts here.

But I'll tell you something that Ilya said to me once a long time ago that has stuck in my head.

Ilya Setsgever.

Yes, my co-founder and the chief scientist of OpenAI and sort of legend in the field.

We were talking about how you would know if a model were conscious or not.

And I've heard many ideas thrown around, but he said one that I think is interesting.

If you trained a model...

on a data set that you were extremely careful to have no mentions of consciousness or anything close to it in the training process.

Like not only was the word never there, but nothing about the sort of subjective experience of it or related concepts.

And then you started talking to that model about here are some things that you weren't trained about.

And for most of them, the model was like, I have no idea what you're talking about.

But then you asked it, you sort of described the experience, the subjective experience of consciousness.

And the model immediately responded, unlike the other questions.