OpenAI launches first embedded assessments with Apollo, METR, Transluce and Goodfire

gdb · x · 2026-11-17

OpenAI is partnering with Apollo Research, METR, Transluce AI and Goodfire AI on "embedded assessments" — giving outside experts deep access to internal models and systems to investigate alignment and test safeguards.

The company says the assessments build on its ongoing alignment and safety research, bringing independent scrutiny to how it identifies and manages risks in its systems. Greg Brockman announced the first round is now launching.

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

Original post →

More from Safety

Safety channel →