OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior. CEO Sam Altman said outside researchers would receive “employee level” access to assess AI safety, but the pilot program appears more restrictive; limits on access and disclosure have raised questions about evaluator independence.
3 reports from 3 publishers confirmed as covering this specific event.
Reporting from 3 identified publishers across this event arc.
These publishers contributed reporting to the broader event history. Not every source addresses the specific development described above.
How this brief is built: The BriefBrief correlates multiple sources into one evolving event brief, updated as new facts emerge.
Page 383 of 22954
Same format. Every time.
Continue reading — sign in or create a free account with