8 commits

Author	SHA1	Message	Date
teknium	47c396c43f	switch to chat completions endpoint to eval closed lab stuff	2025-07-15 11:39:29 +00:00
teknium	982645ce73	Implement proper ties category scoring	2025-07-15 11:16:15 +00:00
pre-commit-ci[bot]	41c847ddf4	[pre-commit.ci] auto fixes from pre-commit.com hooks ... for more information, see https://pre-commit.ci	2025-07-14 09:43:20 +00:00
teknium	ef04098718	glitch	2025-07-14 09:42:44 +00:00
teknium	51d4d52765	Merge branch 'add-pairwise-judge-environment' of https://github.com/NousResearch/atropos into add-pairwise-judge-environment	2025-07-14 09:42:21 +00:00
teknium	9607880f3d	Lots of updates to the environment to cleanup, add more metrics, make more robust - ties has an issue though	2025-07-14 09:39:00 +00:00
pre-commit-ci[bot]	107809260d	[pre-commit.ci] auto fixes from pre-commit.com hooks ... for more information, see https://pre-commit.ci	2025-07-12 11:23:13 +00:00
teknium	e83d796c74	add pairwise judgement environment	2025-07-12 11:15:56 +00:00