←back to thread

Grandmaster-level chess without search

(github.com)
365 points lawrenceyan | 1 comments | 17 Oct 24 19:13 UTC | HN request time: 0.259s | source
Show context
joelthelion ◴[17 Oct 24 20:42 UTC] No.41873554[source]▶
I wonder if you could creatively combine this model with search algorithms to advance the state of the art in computer chess? I wouldn't be surprised to see such a bot pop up on tcec in a couple years.
replies(3): >>41873666 #>>41873900 #>>41900388 #
1. sinuhe69 ◴[21 Oct 24 03:17 UTC] No.41900388[source]▶
Leela, the open source model already (and always) does that and is already much better then the new DeepMind model. No, neural networks are basically curve fitting. You can only do so much approximation without overfitting and there are always positions, which are different enough from the “mainstay” positions that NN can not learn them. DeepMind as always want to impress the public by creating artificial conditions to show its product under better light. But the reality is:

- The Leela open source community had already used transformer architecture to train Lc0 long before the paper (and published it, too!) and got much better result than new DeepMind massive model

- The top engines with with search (Stockfish NNUE, Lc0) beat DeepMind’s model by margins under normal competition’s conditions

- Speaking about efficiency, Stockfish NNUE can run on a commodity PC with only slightly lower ELO. AlphaZero or DeepMind’s new model can not even run to begin with.