Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Stockfish 14

stockfishchess.org

Post reply on HN
Print view View original

21–30 of 207 posts

Re: Stockfish 14

#21

Post by perihelions »

agalunar wrote: post #19
perihelions wrote: post #11

Earlier quoted context omitted.

Chess engines' stdio is for IPC with graphical front-ends, not interactive REPL use. Stockfish isn't really packaged as a standalone software program. Here's an immediately usable browser version (supports WebAssembly with SIMD instructions): https://lichess.org/analysis If you want to experiment with ./stockfish anyway, the protocol documentation is here: https://www.shredderchess.com/chess-features/uci-universal-c.…

Stockfish also has a few non-standard commands, e.g. `eval`, which shows the NNUE derived piece values (among other things), which is pretty cool: $ ./stockfish position startpos eval

[deleted off-topic comment]

Re: Stockfish 14

#22

Post by agalunar »

perihelions wrote: post #21
agalunar wrote: post #19

Earlier quoted context omitted.

Stockfish also has a few non-standard commands, e.g. `eval`, which shows the NNUE derived piece values (among other things), which is pretty cool: $ ./stockfish position startpos eval

[deleted off-topic comment]

I'm getting extra output with NNUE enabled:

https://heptonion.net/9ff70753.html

Notice the diagram titled "NNUE derived piece values" underneath the table for "Contributing terms for the classical eval".

Edit: for anyone interested in the hand-tuned evaluator, it might be worth checking out the Stockfish evaluation guide [1]. (The board in the upper-right corner is interactive!)

[1] https://hxim.github.io/Stockfish-Evaluation-Guide/

Re: Stockfish 14

#23

Post by perihelions »

agalunar wrote: post #22
perihelions wrote: post #21

Earlier quoted context omitted.

[deleted off-topic comment]

I'm getting extra output with NNUE enabled: https://heptonion.net/9ff70753.html Notice the diagram titled "NNUE derived piece values" underneath the table for "Contributing terms for the classical eval". Edit: for anyone interested in the hand-tuned evaluator, it might be worth checking out the Stockfish evaluation guide [1]. (The board in the upper-right corner is interactive!) [1] https://hxim.github.io/Stockfish-E…

Ahh this is my fault for thoughtlessly running an out-of-date version. Sorry!

Re: Stockfish 14

#24

Post by wkavey »

jaimex2 wrote: post #16

Rematch Alpha Zero. Have power consumption restraints. Go!

I think this is a good idea, but in no way should it be the only restrained game. Others could be time restraints (total time per game and/or total time per move), depth restraints (if they both work off of BFS/similar), and probably many other restraints that those more familiar with the engines can come up with.

Definitely throw in a no casteiing game as well.

Re: Stockfish 14

#27

Post by aidenn0 »

make3 wrote: post #17
TchoBeer wrote: post #13

Earlier quoted context omitted.

NNUE is much smaller than Leela's net, and has a much different architecture that's optimized more for CPU. Additionally, Leela uses Monte Carlo Tree Search and Stockfish uses Alpha/Beta pruning.

They say that the dataset is hundreds of Gigs worths of games, so the net must still be really pretty big. Though definitely not directly comparable, dataset of GPT2-xl is 8 million web-pages. What I mean to say is that this is clearly deep learning.

Size of training set is not enough to make it deep learning, right? Doesn't deep learning imply at least one hidden layer?

Re: Stockfish 14

#28

Post by agalunar »

perihelions wrote: post #23
agalunar wrote: post #22

Earlier quoted context omitted.

I'm getting extra output with NNUE enabled: https://heptonion.net/9ff70753.html Notice the diagram titled "NNUE derived piece values" underneath the table for "Contributing terms for the classical eval". Edit: for anyone interested in the hand-tuned evaluator, it might be worth checking out the Stockfish evaluation guide [1]. (The board in the upper-right corner is interactive!) [1] https://hxim.github.io/Stockfish-E…

Ahh this is my fault for thoughtlessly running an out-of-date version. Sorry!

Np! ^_^

(I suppose I should have also disclaimed that I'm running from master rather than the release, so it's possible the output's a bit different.)

Re: Stockfish 14

#29

Post by aidenn0 »

wkavey wrote: post #24
jaimex2 wrote: post #16

Rematch Alpha Zero. Have power consumption restraints. Go!

I think this is a good idea, but in no way should it be the only restrained game. Others could be time restraints (total time per game and/or total time per move), depth restraints (if they both work off of BFS/similar), and probably many other restraints that those more familiar with the engines can come up with. Definitely throw in a no casteiing game as well.

Most chess games are already time constrained (though a ref can call it if someone in a non-winning position is trying to run out the opponents clock)

[edit]

I was imperfectly remembering the rules. If it is theoretically impossible (even with blunders on the player who is out of time's part) for the player with time left to win, then it is a draw.

In addition, a player with less than 2 minutes on the clock may request a draw; see Article 10.2 which includes this subsection:

> a. If the arbiter agrees the opponent is making no effort to win the game by normal means, or that it is not possible to win by normal means, then he shall declare the game drawn. Otherwise he shall postpone his decision or reject the claim.

Post reply on HN