chess_llm_interpretability
fishnet
chess_llm_interpretability | fishnet | |
---|---|---|
3 | 45 | |
167 | 699 | |
- | 1.1% | |
9.5 | 8.8 | |
8 days ago | 5 days ago | |
Jupyter Notebook | Rust | |
- | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
chess_llm_interpretability
-
Manipulating the Internal World Model of a Chess Playing Language Model
The code for this is located here: https://github.com/adamkarvonen/chess_llm_interpretability
- Chess-GPT's Internal World Model
fishnet
-
Chess-GPT's Internal World Model
> The problem is that a stockfish based bot knows some very strong moves, but deliberately plays bad moves so itβs about the right skill level.
What are you basing this on? To me it seems like difficulty is set by limiting search depth/time: https://github.com/lichess-org/fishnet/blob/master/src/api.r...
- Ask HN: What fuel for my data furnace?
- Fishnet: Distributed Stockfish Analysis for Lichess.org
-
What is the deep of analysis of stockfish in lichess?
The LiChess documentation indicates how many nodes are searched: https://github.com/lichess-org/fishnet/blob/master/doc/protocol.md
-
Initial eval graph doesnt change after subsequently increasing depth
The eval graph comes from an analysis done by fishnet. The analysis that you see changing is done locally in the browser on your device. That is why there is a difference.
-
Is Lichess getting slower for people?
YOU can help by running this: https://github.com/lichess-org/fishnet
- January was a month of records for Lichess π - 147,000 concurrent players - 161 million games played - More than 4 million active users - Almost as many new accounts created as November and December combined - 4 billion games in the Lichess DB - Such an amazing start to 2023!
-
Why is Lichess analysis limited to 15 CPUs for me?
Game analyses are made in a distributed way, but only accepted from users they trust. You can check the tool they use for that here and they instructions to use it.
-
chess.com analysis of the same move in back-to-back games
It's not on the user's device and not on their servers. The game analysis is done by fishnet using donated CPU time.
-
If Chess.com made all of their premium features free, would you prefer it over Lichess or would Lichess still be better?
You can run a program on your computer, so that Lichess can run Stockfish analysis using your CPU https://github.com/lichess-org/fishnet
What are some alternatives?
lila - β lichess.org: the forever free, adless and open source chess server β
pgn-tactics-generator - Generate chess puzzles / tactics from a pgn file
online-go.com - Source code for the Online-Go.com web interface
api - Lichess API documentation and examples
stockfish.wasm - WebAssembly port of the strong chess engine Stockfish
fishtest - The Stockfish testing framework
lichobile - lichess.org mobile application
wireguard-install - WireGuard road warrior installer for Ubuntu, Debian, AlmaLinux, Rocky Linux, CentOS and Fedora
Lila - β lichess.org: the forever free, adless and open source chess server β [Moved to: https://github.com/lichess-org/lila]
Tor-IP-Addresses - Hourly checked and updated list of IP Addresses of Tor and Tor Exit Nodes
LinuxGSM - The command-line tool for quick, simple deployment and management of Linux dedicated game servers.
listudy - Listudy - chess training server