Tags: codedeliveryservice/Reckless
Tags
Update default network to v50-441ec316.nnue (#619) STC Elo | 6.86 +- 3.50 (95%) SPRT | 8.0+0.08s Threads=1 Hash=16MB LLR | 2.93 (-2.25, 2.89) [0.00, 3.00] Games | N: 9872 W: 2551 L: 2356 D: 4965 Penta | [22, 1095, 2515, 1274, 30] https://recklesschess.space/test/9756/ LTC Elo | 5.11 +- 2.91 (95%) SPRT | 40.0+0.40s Threads=1 Hash=64MB LLR | 2.89 (-2.25, 2.89) [0.00, 3.00] Games | N: 12862 W: 3223 L: 3034 D: 6605 Penta | [3, 1400, 3437, 1587, 4] https://recklesschess.space/test/9757/ STC DFRC Elo | 6.16 +- 3.11 (95%) SPRT | 8.0+0.08s Threads=1 Hash=16MB LLR | 3.02 (-2.25, 2.89) [0.00, 3.00] Games | N: 10264 W: 1763 L: 1581 D: 6920 Penta | [31, 874, 3148, 1040, 39] https://recklesschess.space/test/9758/ Bench: 3016642
Introduce PCM updates to TT early cutoffs (#615) Elo | 2.28 +- 1.75 (95%) SPRT | 8.0+0.08s Threads=1 Hash=16MB LLR | 2.90 (-2.25, 2.89) [0.00, 3.00] Games | N: 38936 W: 9854 L: 9599 D: 19483 Penta | [80, 4541, 9964, 4810, 73] https://recklesschess.space/test/9576/ Bench: 3652331
Simplify away low impact FDS reduction rules (#567) STC Elo | 3.05 +- 2.76 (95%) SPRT | 8.0+0.08s Threads=1 Hash=16MB LLR | 2.92 (-2.25, 2.89) [-3.00, 0.00] Games | N: 15604 W: 3974 L: 3837 D: 7793 Penta | [26, 1816, 3989, 1937, 34] https://recklesschess.space/test/8941/ LTC Elo | 0.80 +- 2.09 (95%) SPRT | 40.0+0.40s Threads=1 Hash=64MB LLR | 3.00 (-2.25, 2.89) [-4.00, 0.00] Games | N: 24870 W: 6076 L: 6019 D: 12775 Penta | [8, 2858, 6642, 2923, 4] https://recklesschess.space/test/8947/ Bench: 3666261
Release of Reckless v0.8.0 (#474) Reckless has come a long way since its early days as a solo project. During the [FIDE & Google Efficient Chess AI Challenge][1], I worked with Shahin (@peregrineshahin) on the team that finished in second place. After the competition in late February 2025, the whole search algorithm started being rebuilt from the ground up. Shortly after, @peregrineshahin joined the project as one of its co-authors, with Styx (@styxdoto) joining a bit later. Together, we have transformed Reckless into a formidable chess engine, moving far and beyond the capabilities of its predecessor. We are now releasing Reckless v0.8.0, one of the strongest chess engines in the world and the strongest chess engine written in Rust. Playing Strength Reckless v0.8.0 is enormously stronger than the previous release. In practical terms, v0.7.0 is no longer a meaningful opponent of measuring progress. Nevertheless, using a balanced opening book `8moves_v3`, the results of the progression are as follows: STC 8.0+0.08s Elo | 334.77 +- 6.38 (95%) Conf | 8.0+0.08s Threads=1 Hash=16MB Games | N: 10116 W: 7583 L: 38 D: 2495 Penta | [0, 4, 216, 2127, 2711] https://recklesschess.space/test/7421/ LTC 40.0+0.40s Elo | 301.49 +- 8.15 (95%) Conf | 40.0+0.40s Threads=1 Hash=64MB Games | N: 5004 W: 3506 L: 2 D: 1496 Penta | [0, 0, 150, 1200, 1152] https://recklesschess.space/test/7422/ Update highlights Syzygy Tablebase Support We have added support for Syzygy endgame tablebases with up to 7 pieces, thanks to the [Fathom][2] library. Chess960 Support Reckless can now play Chess960 (Fischer Random Chess), with full support for castling rules and position setup. It also handles assymmetrical starting positions, commonly referred to as Double Fischer Random Chess (DFRC). NNUE Improvements The originally used custom network trainer has been replaced with [Bullet][3], a specialized ML library developed by @jw1912. Over 30 iterations of stronger networks have been merged, leading to a multi-layer NNUE model trained on billions of positions. Looking Ahead Since the last release, we have made over 500 commits, and the project remains very much active. We are looking forward to making Reckless better, adding new features, and more! [1]: https://www.kaggle.com/competitions/fide-google-efficiency-chess-ai-challenge [2]: https://github.com/jdart1/Fathom [3]: https://github.com/jw1912/bullet Bench: 2052487 Co-Authored-By: Shahin M. Shahin <41402573+peregrineshahin@users.noreply.github.com> Co-Authored-By: Styx <164851643+styxdoto@users.noreply.github.com>
PreviousNext