FrontierML: A challenging, end-to-end machine learning benchmark

ResearchAnthropic gives METR inside access to audit its AI models and safety practicesOct 15 · 2 sources

ResearchPlan or Retrieve First? A Scale Study of Tool Discovery ArchitecturesOct 15 · 3 sources

ResearchMeta’s new terms may allow it to train AI on news sites for freeOct 16 · 5 sources

ResearchGoogle says self-improving AI isn't anywhere closeOct 14 · 2 sources

Covered by 1 source