1.8Kпросмотров
26.6%от подписчиков
11 марта 2026 г.
Score: 2.0K
Research note: Many SWE-bench-Passing PRs Would Not Be Merged into Main https://metr.org/notes/2026-03-10-many-swe-bench-passing-prs-would-not-be-merged-into-main/
J
Just links
@j_links6.7K подп.
1.8K
просмотров
163
символов
Нет
эмодзи
Нет
медиа
Другие посты @j_links
EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Langua👁 2.4KLATENT Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data https://zzk273.git👁 2.4KPreventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments https://arxiv.or👁 2.3KTech boss uses AI and ChatGPT to create cancer vaccine for his dying dog https://www.theaustralian.👁 2.2KEfficient Exploration at Scale https://arxiv.org/abs/2603.17378👁 2.1K
Все посты канала →