OpenAI brings outside experts from Apollo, METR, Transluce, Goodfire for embedded safety assessments

austinc3301 · x · 2026-11-17

OpenAI announced "embedded assessments": a program giving outside experts from Apollo Research, METREvals, TransluceAI, and GoodfireAI deep access to its internal models and systems to investigate alignment and test safeguards.

The initiative builds on OpenAI's ongoing alignment research and adds independent scrutiny of how the company identifies and manages risks in its systems. Observers quickly called on Anthropic to follow suit, hinting at an industry-wide transparency race.

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

Original post →

More from Safety

Safety channel →