←back to thread

'World Models,' an old idea in AI, mount a comeback

(www.quantamagazine.org)
204 points warrenm | 3 comments | 02 Sep 25 16:53 UTC | HN request time: 0.681s | source
Show context
BariumBlue ◴[02 Sep 25 19:53 UTC] No.45108178[source]▶
> When researchers attempt(opens a new tab) to recover [something like] a coherent computational representation of an Othello game board they instead find [bags of heuristics]

Humans don't exactly have a full representation of board space in their head either. Notably, chess masters and amateurs can memorize completely random board positions as well as the other. I'd think neither could memorize 64 chess pieces in random positions on a board.

replies(2): >>45108240 #>>45109651 #
1. mym1990 ◴[02 Sep 25 19:58 UTC] No.45108240[source]▶
For whatever its worth, I bet the chess master would be able to instantly identify that it is a random/invalid board position, aka an invalid world state. I think the experiment you are alluding to gave both groups a very limited amount of time to look at the board. Given enough time, both groups would definitely be able to memorize 64 pieces on a board.
replies(1): >>45108718 #
2. aurelwu ◴[02 Sep 25 20:39 UTC] No.45108718[source]▶
I do think even the most amateur of amateurs would be able to recognize instantly that a chess board with 64 pieces on it is a invalid game state.
replies(1): >>45115766 #
3. mym1990 ◴[03 Sep 25 13:47 UTC] No.45115766[source]▶
Sorry, I meant that masters could identify smaller sets of pieces as invalid instantly, but that both masters and amateurs would be able to memorize 64 piece board with enough time.