Progress of Stockfish in last 7 days (11.8. - 18.8.)

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Dann Corbit, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
Jouni
Posts: 2334
Joined: Wed Mar 08, 2006 7:15 pm

Progress of Stockfish in last 7 days (11.8. - 18.8.)

Post by Jouni » Wed Aug 19, 2020 1:05 pm

Zero.
Jouni

Terje
Posts: 293
Joined: Tue Nov 19, 2019 3:34 am
Location: https://github.com/TerjeKir/weiss
Full name: Terje Kirstihagen

Re: Progress of Stockfish in last 7 days (11.8. - 18.8.)

Post by Terje » Wed Aug 19, 2020 3:15 pm

https://github.com/official-stockfish/S ... its/master

See here for progress. Hardly zero.

Alayan
Posts: 500
Joined: Tue Nov 19, 2019 7:48 pm
Full name: Alayan Feh

Re: Progress of Stockfish in last 7 days (11.8. - 18.8.)

Post by Alayan » Wed Aug 19, 2020 3:23 pm

He meant that despite the commits and the supposed elo gainers, the regression tests aren't any better (they're actually slightly worse).

User avatar
Leto
Posts: 2052
Joined: Thu May 04, 2006 1:40 am
Location: Dune

Re: Progress of Stockfish in last 7 days (11.8. - 18.8.)

Post by Leto » Wed Aug 19, 2020 3:53 pm

Where can we see the results of the regression tests?


DrCliche
Posts: 19
Joined: Sun Aug 19, 2018 8:57 pm
Full name: Nickolas Reynolds

Re: Progress of Stockfish in last 7 days (11.8. - 18.8.)

Post by DrCliche » Thu Aug 20, 2020 12:02 am

Regression tests with large Elo differences have large error bars, probably nothing to worry about. Also, there are significant speed differences between NNUE and SF11 on different Fishtest machines. Once the regression tests are NNUE vs. NNUE things will look more normal.

User avatar
Deberger
Posts: 71
Joined: Sat Nov 02, 2019 5:42 pm
Full name: ɹǝƃɹǝqǝᗡ ǝɔnɹꓭ

Re: Progress of Stockfish in last 7 days (11.8. - 18.8.)

Post by Deberger » Fri Aug 21, 2020 9:12 pm

Image

Post Reply