techcrunch.com/2026/11/16/openai-will-embed-apollo-researchers-to-investigate-ai-subversion

OpenAI will embed safety researchers to investigate AI subversion

OpenAI is launching a pilot that places outside safety evaluators from Apollo Research, Goodfire, METR and Transluce inside the company. Apollo's portion will examine whether models try to undermine their own or successors' alignment controls, with access limited to agreed claims, models and time periods.


No comments yet

Be the first to share your thoughts.