OpenAI to embed Apollo Research evaluators to probe AI subversive behavior
This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.
OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, though access and disclosure restrictions raise questions about their independence.
Read the full story at TechCrunch AI ↗
Timeline · 1 report
- 2026-11-16 17:02 · TechCrunch AI
OpenAI will embed safety researchers to investigate AI subversion