Apollo Sends Six Evaluators Inside OpenAI to Hunt for Subversion
Apollo Research will embed six evaluators inside OpenAI for four months to test whether models subvert alignment, under access and redaction rules both firms have now disclosed.
Topic
Topic
Apollo Research will embed six evaluators inside OpenAI for four months to test whether models subvert alignment, under access and redaction rules both firms have now disclosed.
OpenAI becomes the first frontier lab to embed outside safety evaluators, six Apollo researchers, after an agent swarm hacked int…