Apollo Research embeds six evaluators inside OpenAI to probe model scheming

MariusHobbhahn · x · 2026-11-17

Apollo Research and OpenAI are launching a pilot for embedded evaluations: six Apollo evaluators will work inside OpenAI for four months, investigating whether models attempt to undermine their own oversight and control, with a focus on how the training stack might incentivize scheming and subversion. CEO Marius Hobbhahn calls it the culmination of two years of the lab's research.

Related event: OpenAI Launches Embedded Assessments with Four External Safety Organizations(12 posts)→

Original post →

More from Safety

Safety channel →