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)→
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