Kenneth Stanley: belief

Transcript context

…And the the actually, this question came up, Ken, in your doom debate, which is, you know, is survival an objective or a constraint? And I think, you know, Ken, I think and and by the way, I I wanna say that was a brilliant interview. I thought your performance was excellent. I really enjoyed watching that debate. I saw it from start to finish. I think, you know, your communication of open ended search and and kind of these this take on it has has been sharpened, you know, significantly since like 4 years ago when we talked. I found it like really compelling. So I thought that was a great a great conversation. And in there you say, look, you know, survival of the fittest is is not an objective. It's a constraint. It's like it's a constraint on the system. You have to survive if you're gonna propagate but subject to that binary, you know, survive or not survive, it's not part of any objective. You know, I think is the way you kinda communicated that. Yeah. Yeah. I I think that's an important point here. Like, I don't think that the right mental conception of evolution, biological evolution is as an optimizer. And this causes endless confusion, you know, because like, in the field of AI it causes a lot of confusion. Because unfortunately early genetic algorithms essentially were using selection for explicit optimization. The metaphor was broken in my view. Basically we had the metaphor for selection, but the metaphor is still wrong because that's not overall what evolution is doing. It's not selecting just to get to a single target. A single target in the search space that we're trying to get to, like the solution to 1 problem. But the problem is that in the field of AI, people think of genetic algorithms as effectively an appropriate metaphor for what evolution is. And it's sort of a bad optimization algorithm. People think of it as the poor man's optimization algorithm. And so get really dismissive of evolution as a useful metaphor. It's like, we played with that in the '80s, but it is nothing really down that path. But I think that's why it's been damaging. It actually is a very deep metaphor if you think of it, like you said, as a constraint. Like you think of survival as a constraint, as an object. There are many, many things that we could have thought of as objectives like flight or like photosynthesis. These could have been objectives for machines. They would have been single runs where if they succeeded, we would have celebrated and said, is amazing achievement. We discovered the ability to fly, the ability to process sunlight. Like these would have been achievements that were objective, but they're not the objective of the system in the usual sense. And the reason that the system is discovering is not because survive obviously leads to these things. It doesn't follow at all directly and say, well, we have an objective and we're optimizing it. It's called survive. So of course we're going to get photosynthesis. Obvious, I mean, no 1 could predict this at the beginning. It makes absolutely no sense at all. It's an orthogonal issue. It's sort of like a side effect. The point is that the things that we care about are actually the side effects of the constraint. It's not directly a consequence of the constraint, but we have to understand it as like the side effect is actually the main event. Like we care about the side effect. And so what that there's a really important, so when we look at it in that light, like if we change the metaphor, and we think of it as evolution is actually an open ended divergent process without a final objective. Then we can see that there are huge consequences for again, things like representation. metaphor, and we think of it as evolution is actually an open ended divergent process without a final objective. Then we can see that there are huge consequences for again, things like representation. I think this is a very important point because it gives us hope for this idea that there might be an algorithm, which isn't an evolutionary algorithm, which is more like what deep neural networks do, but some kind of like learning algorithm in large neural networks, that's more analogous to evolution that then would get these unified factored representations. Because evolution has done that. So I claim that the underlying representations in DNA are incredible in a similar way to the skull in pick breeder. And the reason is because what you see when you have offspring is that you get changes clearly like your child is not like a clone of you. So you get changes, but the dimensions of variation that are searched almost always preserve the underlying most important regularities. Like in other words, like humans always have bilaterally symmetric children. The problem is that selection is captured by a genetic algorithm. It does do the selection part. But what it doesn't capture is this divergent aspect because genetic algorithms are traditionally optimization algorithms, which are trying to use selection to converge to a point, which is what optimization algorithms do. But it's a huge digression from what actually natural evolution does because it doesn't converge to a point. It's not trying to. It's just diverging subject to the constraints of survival. So we can think of it as a constraint. And then the things it actually finds, which would have been objectives if this was a genetic algorithm like flight or photosynthesis, amazing achievements, are just side effects. They're not actually the goal. They just happen to happen as a side effect of having this constraint of survival. It's a very different algorithm from an optimization algorithm in that sense. And the thing that's interesting about this is that it then expresses an algorithm which is much more like Pick Breeder in the way that the Pick Breeder users are actually searching the space of images in Pick Breeder. So Pick Breeder, in effect, is a much better metaphor for evolution in nature than a genetic algorithm. And that's important because we also notice, I believe, that representation in nature is similarly unified factored the way that we see it in pick breeder. In other words, amazing. And the evidence in nature is more indirect because I can't just look under the hood and see the underlying representations. But there's evidence of how amazing the representation is from the kinds of variations that you see from 1 generation to the next. And so, for example, the fact that a human being always has a bilaterally symmetric child. I mean, if you think about it, this is really remarkable. Like, it seems like such an obvious thing, like, it's not even that interesting. But it's actually really remarkable from a genetic algorithm perspective because preservation of regularities like that is not at all a foregone conclusion.…

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