Apollo Research and OpenAI launch an embedded evaluation pilot to investigate whether models attempt to undermine oversight of themselves
AI summary
Apollo Research and OpenAI launch an embedded evaluation pilot; six evaluators will be embedded at OpenAI for four months to investigate whether models will attempt to undermine oversight and control of themselves.
Full text · Original
We're launching a pilot towards embedded evaluations with @OpenAI.
Six evaluators from Apollo Research will work within OpenAI for four months, investigating whether models attempt to undermine their own oversight and control.