{"slug": "leela-chess-zero", "name": "Leela Chess Zero", "category": "other", "category_name": "Other software", "description": "", "recommenders": 3, "commenters": 6, "warners": 0, "score": 3.538, "rising": 1.67, "first": "2025-11-05", "latest": "2026-09-26", "why": "Heavily train a deep learning model for chess and you get Leela, an absolutely monster.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 3, "compare": 0, "warn": 0}, "spark": [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Heavily train a deep learning model for chess and you get Leela, an absolutely monster.", "kind": "", "icon": true, "domain": "lczero.org", "github_repo": null, "official_url": "https://lczero.org/", "pricing": "", "aliases": ["Leela Chess Zero"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 797753217, "item_id": 49859576, "url": "https://news.ycombinator.com/item?id=49859576", "by": "jeremyjh", "date": "2026-09-26", "version": null, "stance": "recommend", "quote": "Heavily train a deep learning model for chess and you get Leela, an absolutely monster.", "excerpt": "Absolutely it will. You have to run them in an environment without tools because today they just turn on stockfish if you ask on claude.ai. These models are strong at math and coding because they have been heavily trained for it in post-training. That is where a majority of the gains have come from in the past two years. That has absolutely no impact on chess ability. Heavily train a deep learning model for chess and", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: A Claude Code skill to analyze your chess games"}, {"id": 793132048, "item_id": 49570753, "url": "https://news.ycombinator.com/item?id=49570753", "by": "sincerely", "date": "2026-09-04", "version": null, "stance": "recommend", "quote": "It's humbling to lose starting up a queen", "excerpt": "If anyone wants to know more about the chess model: https://lczero.org/blog/2024/12/the-leela-piece-odds-challenge-what-does-it-take-you-to-win-against-leela/ You can choose which piece it's missing. It's humbling to lose starting up a queen", "context": "", "use_case": "", "switched_from": "", "story": "Go grandmaster Shin defeats AI KataGo with a two-stone handicap"}, {"id": 733168161, "item_id": 45823010, "url": "https://news.ycombinator.com/item?id=45823010", "by": "harryf", "date": "2025-11-05", "version": null, "stance": "recommend", "quote": "the best chess models like Leela Chess Zero use deep neutral networks", "excerpt": "We need to stop using AI as an umbrella term. It\u2019s worth remembering that LLMs can\u2019t play chess and that the best chess models like Leela Chess Zero use deep neutral networks. Generative AI - which the world now believes is AI, is not the same as predictive / analytical AI. It\u2019s fairly easy to demonstrate this by getting ChatGPT to generate a new relatively complex spreadsheet then asking it to analyze and make chang", "context": "", "use_case": "", "switched_from": "", "story": "I\u2019m worried that they put co-pilot in Excel"}]}], "caveats": [], "who": [], "tags": [], "use_cases": [], "compared": [{"slug": "stockfish", "name": "Stockfish", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49857528", "title": "Show HN: A Claude Code skill to analyze your chess games", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49544762", "title": "Go grandmaster Shin defeats AI KataGo with a two-stone handicap", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49466917", "title": "Small Models Have Arrived", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47077358", "title": "What Is a Centipawn Advantage?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47049845", "title": "Chess engines do weird stuff", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=45820872", "title": "I\u2019m worried that they put co-pilot in Excel", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {}, "2026-01": {}, "2026-02": {"neutral": 2}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"neutral": 1}, "2026-09": {"recommend": 2}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 797753217, "item_id": 49859576, "url": "https://news.ycombinator.com/item?id=49859576", "by": "jeremyjh", "date": "2026-09-26", "version": null, "stance": "recommend", "quote": "Heavily train a deep learning model for chess and you get Leela, an absolutely monster.", "excerpt": "Absolutely it will. You have to run them in an environment without tools because today they just turn on stockfish if you ask on claude.ai. These models are strong at math and coding because they have been heavily trained for it in post-training. That is where a majority of the gains have come from in the past two years. That has absolutely no impact on chess ability. Heavily train a deep learning model for chess and", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: A Claude Code skill to analyze your chess games"}, {"id": 793132048, "item_id": 49570753, "url": "https://news.ycombinator.com/item?id=49570753", "by": "sincerely", "date": "2026-09-04", "version": null, "stance": "recommend", "quote": "It's humbling to lose starting up a queen", "excerpt": "If anyone wants to know more about the chess model: https://lczero.org/blog/2024/12/the-leela-piece-odds-challenge-what-does-it-take-you-to-win-against-leela/ You can choose which piece it's missing. It's humbling to lose starting up a queen", "context": "", "use_case": "", "switched_from": "", "story": "Go grandmaster Shin defeats AI KataGo with a two-stone handicap"}, {"id": 791571697, "item_id": 49473231, "url": "https://news.ycombinator.com/item?id=49473231", "by": "brucehoult", "date": "2026-08-28", "version": null, "stance": "neutral", "quote": "I guess you missed Leela then.", "excerpt": "I guess you missed Leela then. And in 2020 Stockfish 12 adding some NN evaluation. And then in 2023 Stockfish 16 entirely removing the classical position evaluation code. https://stockfishchess.org/blog/2023/stockfish-16/", "context": "", "use_case": "", "switched_from": "", "story": "Small Models Have Arrived"}, {"id": 754081872, "item_id": 47130117, "url": "https://news.ycombinator.com/item?id=47130117", "by": "knuckleheads", "date": "2026-02-23", "version": null, "stance": "neutral", "quote": "there is an interesting thing that lc0 has been doing as well", "excerpt": "Yep, exactly. I spent a lot of time trying to figure out better ways for interpreting the evaluations of engines for https://www.schachzeit.com/en/openings/barnes-opening-with-d5/gedult-gambit and I ended up liking WDL much better than centipawns. A blunder defined in terms of decreasing your chance of winning by such and such percentage is, to me, a much better definition than a blunder losing such and such material", "context": "", "use_case": "", "switched_from": "", "story": "What Is a Centipawn Advantage?"}, {"id": 752822929, "item_id": 47051433, "url": "https://news.ycombinator.com/item?id=47051433", "by": "helloplanets", "date": "2026-02-17", "version": null, "stance": "neutral", "quote": "Like Leela Chess Zero [2] vs. Stockfish.", "excerpt": "There's the TCEC [0] which is a big thing in some circles. Stockfish does lose every now and then against top engines. [1] Usually it's two different engines playing against one another, though. Like Leela Chess Zero [2] vs. Stockfish. In that hypothetical of running 2 instances of Stockfish against one another on a modern laptop, with the key difference being minutes of compute time, it'd probably be very close to 1", "context": "", "use_case": "", "switched_from": "", "story": "Chess engines do weird stuff"}, {"id": 733168161, "item_id": 45823010, "url": "https://news.ycombinator.com/item?id=45823010", "by": "harryf", "date": "2025-11-05", "version": null, "stance": "recommend", "quote": "the best chess models like Leela Chess Zero use deep neutral networks", "excerpt": "We need to stop using AI as an umbrella term. It\u2019s worth remembering that LLMs can\u2019t play chess and that the best chess models like Leela Chess Zero use deep neutral networks. Generative AI - which the world now believes is AI, is not the same as predictive / analytical AI. It\u2019s fairly easy to demonstrate this by getting ChatGPT to generate a new relatively complex spreadsheet then asking it to analyze and make chang", "context": "", "use_case": "", "switched_from": "", "story": "I\u2019m worried that they put co-pilot in Excel"}]}