AI May Be Conscious. Visual Illusions Suggest It.

Ajouté : 2026-06-04

[00:00:00]Do you believe consciousness is substrate independent?

[00:00:02]>> Yes.

[00:00:03]>> Why?

[00:00:03]>> The experiments we started running and my interactions with AI models indicate they probably have very similar experiences to us. So, it would be somewhat surprising if it was unique to meat-like products.

[00:00:19]>> What are the experiments that indicate they have experiences?

[00:00:22]>> Uh the visual illusions experiments we started running. They seem to be getting illusions in many times in exactly the same way as human visual system.

[00:00:33]Uh interactions with those systems, not by us, but by others, indicates they have preferences.

[00:00:40]They have internal states. They get frustrated. They get happy. They They are very similar to what I would expect another conscious being to experience.

[00:00:52]>> You mean to say that they act in a way that is consistent with what we would act like if we were frustrated and happy and so forth. But you've just attributed they are happy. They I'm asking about the attribution.

[00:01:04]>> Yeah, and that's the same what I do with other human beings, right? I have no reason other than I kind of generally give this benefit of a doubt to beings who are capable of exhibiting certain behaviors. Just treat them as equals. I treat AIs and other humans as equal class. If they can perform same things, I see no reason to discriminate against one or the other. And either I have to deny consciousness to many humans or grant it to LLMs. So, again, we rely on neural correlates. We rely on behavioral signatures, self-reports.

[00:01:38]With AIs, we're starting to be able to poke a little bit at their internal workings, and we do see similar things we see with neuroscience and human brains.

[00:01:50]>> And suppose we didn't, but they gave the same output.

[00:01:53]Because it would still pass your behavioral test.

[00:01:55]>> So, if it was like a large lookup table, and then I said something, it just hashed that and looked up exact text string and gave me plausible response, it would be much harder to make an argument that there is some magic happening in there, but that's not how we build them. We got inspired in large part by neuroscience of a human brain. We copied it to the best of our ability. Obviously, it's not an exact replica or even a good simulation, but there is enough similarities when our visual component of human cortex is very similar to what we see in those models in terms of how we process data, in terms of what errors we make. So, it's trained on same data as human children in many ways, internet. It's after the fact that it trained to be more like a human. So, it's not completely insane to think it also experiences something similar to what humans do.