News for hackers. Stuff that matters.
Re:AI masters Minecraft: DeepMind program finds diamonds wit... by d0mine on Monday April 07, 2025 @01:58PM (#43614142)
Isn’t it exactly what alphazero did?

“AlphaZero was trained solely via self-play using 5,000 first-generation TPUs to generate the games and 64 second-generation TPUs to train the neural networks, all in parallel, with no access to opening books or endgame tables. After four hours of training, DeepMind estimated AlphaZero was playing chess at a higher Elo rating than Stockfish 8; after nine hours of training, the algorithm defeated Stockfish 8 in a time-controlled 100-game tournament (28 wins, 0 losses, and 72 draws).” [emphasis added] https://en.wikipedia.org/wiki/AlphaZero

Re:AI masters Minecraft: DeepMind program finds diamonds wit... by red75prime on Monday April 07, 2025 @03:02PM (#43614732)
I thought that it might be a rare chance to invoke the NFL theorem appropriately, but I guess I was wrong. The NFL talks about a uniform distribution of problems. A case that is probably never the case. At least for habitable universes.

Nevertheless, the theorem basically states that there are games where AlphaZero will be beaten by another algorithm. Even if those games are nonsensical from our point of view.

Re:AI masters Minecraft: DeepMind program finds diamonds wit... by Xcelerate on Monday April 07, 2025 @03:58PM (#43615297)
> I thought that it might be a rare chance to invoke the NFL theorem appropriately, but I guess I was wrong

Haha, I wouldn’t feel bad. It’s one of the most misunderstood theorems, and I don’t think I’ve ever seen it invoked correctly on a message board.

Re:AI masters Minecraft: DeepMind program finds diamonds wit... by tmtvl on Monday April 07, 2025 @06:04PM (#43616459)
I forget, was it Alpha or one of the others (Leela, Kata, FineArt,...) which had a weakness against... I wanna say the Micro Chinese (?), where it would consistently play the same suboptimal sequence that let players beat it easily if they took that path.
Re:AI masters Minecraft: DeepMind program finds diamonds wit... by voidmain on Tuesday April 08, 2025 @10:45PM (#43628438)
Games drawn from this uniform distribution can't even be implemented in our physical universe (you would need exponentially large lookup tables to store the rules). There is no chance of ever encountering any of them.

Of course, there are "games" like "invert sha-512" that can be implemented in our world but are probably impractical to learn. But NFL has nothing to say about them; a game that simple has zero measure in a uniform distribution over problems.