OpenAI opens internal models to METR, Apollo for alignment audits

petrusenko_max · x · 2026-11-17

OpenAI is partnering with Apollo Research, METR, Transluce, and Goodfire on "embedded assessments," giving outside experts access to internal models and systems to investigate alignment and test safeguards. METR will independently examine OpenAI's largest RL run to date for misaligned behavior its own monitors may have missed; Apollo Research will test whether models attempted "subversion" during internal use. Commenter petrusenkomax adds that assessments see the model, not the wiring — a stray stop file in one script kept his daily invites off for 6 days undetected.

Related event: OpenAI Launches Embedded Assessments with Four External Safety Labs(19 posts)→

Original post →

More from Safety

Safety channel →