Dries Smit: recommendation

Transcript context

…And what I meant by that was, you know, yes, we could solve problems. We could do hill climbing, you know, when we knew what the problem was. And maybe you would agree that in Arc AGI 3, when we know what the goal is, it becomes a hill climbing problem. But it feels like the challenge is abstraction. And it's almost unfair that Charle is doing this action efficiency thing. I mean, in my opinion, what he should do is, yeah, you do it the dumb way the 1st time and then you compress that into reusable knowledge and it's in your library. And then the next problem that comes up which should ostensibly be using what you just learned in the 1st game, then you become more efficient. So you kind of become more efficient over time because you're compressing knowledge. That kind of feels like the goal to me. Yes. So there's actually been discussion in the community about, let's say for Arcadia 4 having that as 1 of the goals. You play a game, you solve it as in like a large compute or action budget and then you have to play it again and you have to do like a speed run through it to improve it. So I think that is important, but I also think action efficiency is a practical step to reduce just brute force solutions. It counteracts that. You have to explore in a more intelligent way and it kind of makes sense in real world environments as well like computer use, coding agents. You can't just explore every possibility. You have to do it in an intelligent way and improve, yeah, using some heuristic. And I think, yeah, I think it makes sense to not always have like, just all the actions available to you. Okay. But even on it on RKGI 3 though, you do have the goal and it's a hill climbing problem, I guess you still can't brute force it because you get dinged on efficiency. But in principle you could if you had enough computation.…

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