OpenAI's third-party safety assessments fall short of promised employee-level access

trevposts · x · 2026-11-17

OpenAI announced "embedded assessments" with Apollo Research, METR, Transluce and Goodfire, giving outside experts deep access to internal models to probe alignment and test safeguards. But Sydney Von Arx argues this is far from Sam Altman's promised "employee-level access":

The author's takeaway: OpenAI is banking on nobody checking the details.

Related event: Researchers Say OpenAI's Embedded Safety Evaluations Fall Short(2 posts)→

Original post →

More from Safety

Safety channel →