Nathan Labenz: observation

Transcript context

…lowing computational functionalism. I understand. It means, I have to say, the simple RL algorithm is conscious when it's training. To me, this like localizes a lot of concern on the training process. But indeed, if there are systems that are capable of doing this sort of learning online, which we know full well LLMS are capable of doing, they do something like that looks in activation space in forward pass like stochastic gradient descent, then the concern falls there too, if you have systems that are doing online learning. So anyway, this is my, this is sort of my whole, my whole shtick. If, you know, I have to sort of put my cards on the table and say, what do I think consciousness is? It's not that I think it's a grand mystery. I, it's something of this general shape. What I will say is that the, in the work that I'm doing, I do not want people to have to either you and the people listening to this will fundamentally think that this makes sense or fundamentally think it doesn't or be very skeptical or something. I do not want that reaction to cloud. All of the other work I'm doing, like everything else we've talked about in this podcast, is completely orthogonal to my pet theories about consciousness. Now, you might think that I'm studying RL and valence in RL because I actually do believe that something like this is going on. And you would be right. That's why I'm I'm looking at that as a model Organism. but i want those results and i want that research to stand on its own without having to get on the like cameron 's theory number five hundred and one about consciousness. I'm not asking people to do that to entertain the the work I'm doing or to entertain Anthropics welfare card or any of that sort of thing. One of the one that comes to mind you had actually mentioned last time, but I also think is quite compelling is the seemingly quite strong inverse correlation between the intensity of our consciousness or the sort of resolution, you might say, and how much we are learning as we go. And I think that you used the example of driving last time where it was like when you're first learning to drive, you are very conscious of what you're doing. And then you can have this sort of, you know, autopilot experience, which obviously we can have that across many aspects of life. But the relationship there between focus and sort of it's there's like a time dilation effect that seems to happen when learning or when experiencing novel things in general that does also seem to kind of gesture or, you know, nudge one toward thinking that there's some like pretty deep relationship between between the two concepts. All right, you made a documentary, which I guess in some sense is what you're here to promote, although we've done everything. But I don't know to what degree you've actually been out in the maybe tell us a little bit about the documentary. What's the point of it? I've watched it. It's for a much more general audience than this podcast. I don't know to what degree you're spending your time trying to communicate about these issues to a general audience aside from the documentary. or how much you feel like you have like got reps in terms of trying to go to somebody who you know has a little grounding or a little you know mechanistic understanding of AI 's or whatever and try to have conversations of of this not this sort but you know around these topics. Yeah, I guess. Why did you decide to make a documentary? How is it? How are you finding it to try to talk to people outside of the AI bubble about these issues? And maybe one thing you could tease about the documentary is a conversation you had with Sam Altman that isn't isn't in the film, but you describe in in quite a bit of detail in the film. And maybe that'll be something that will motivate listeners of this podcast to go check out the full documentary. Yeah, absolutely. so look i have to say at the outset i appreciate you saying this is my documentary but this in in every sense is my good friend milo reed 's documentary. He, I was doing my work, plodding along, you know, talking to folks like you, doing the research I've described and began to share this with Milo, who I went to Yale with undergrad. He's a philosopher and a filmmaker. we've been like you know we're we're we've been close friends for a while keep each other sort of abreast of of the other 's life. Told me about my research. He kept getting more and more sort of interested in, like he's interested in consciousness. He's, he's deep in the sort of philosophy of consciousness and understanding how, how this, you know, connects to, to big questions. And it actually, the, what happened was I sent him a conversation that I had with an AI system, which is itself a piece of the documentary. it's it is a bizarre interaction as i hope someone can gather from the three and a half hours we've been going at it. I do not regard this conversation as proof or anything like it that these systems are conscious. But it was an incredibly bizarre interaction. It was unsettling. I thought to record it because it was the first time I engaged with the system and it seemed incredibly sophisticated and lifelike. And I was like, OK, I'm an I'm a consciousness researcher talking to the system. Make sense to just like record this, You know, in some sense, maybe this is maybe this is experimental data. I was very glad that I recorded it because it was an incredibly bizarre interaction. I went away that I and, and most of people have listened to it would not would not predict it. It would go. I sent this conversation to Milo. And that day he literally quit his job. He was doing something entirely separate. And he set out, he said, people need to know what's going on here. This is too weird. This is too crazy. He was also clear on the fact that very few people, especially at that time, the numbers have grown a little bit, but not not much since we, since we filmed this, very few people were working on these issues. And he was like, this is too good, too interesting not to attempt to make make a movie about. And I was like, OK, haha, sounds good. The kid actually quit his job, actually bought a camera, showed up in New York where I live, you know, a couple weeks later and started making this movie. And he got some of the most interesting people who are in the space. jeff sibo 's in it. Ben Gertzel is in it. A lot of really cool Yale professors are in it, some of whom are former professors, chair of the cognitive science department. AI systems themselves are in the dock. And yeah, it does. It does, you know, follow me and my research around for obvious reasons. I was the sort of hook into the space that that Milo had.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.