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)→
More from Safety
- Flights, banks and Microsoft hit by mass outages; officials deny cyberattack — AaronBergman18 · 2026-11-17
- Kelsey Piper: AI labs have overwhelming commercial incentive to redact audit reports — NathanpmYoung · 2026-11-17
- Critical systems keep having unexplained outages that officials claim are unrelated — josh_bickett · 2026-11-17
- Pedro Domingos clashes with Neel Nanda: machines don't have values, says consensus — pmddomingos · 2026-11-17
- Anthropic's Recursive Self-Improvement Alarm Reportedly Triggered, Security Push Mandated — ForgotMyParachute · 2026-11-17
- CMU researcher warns aggregated chatbot analysis can leak sensitive research insights — niloofar_mire · 2026-11-17