# OpenAI will embed safety researchers to investigate AI subversion

OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, but restrictions on access and disclosure raise questions about their independence.



## 질문과 답변



## 출처
- TechCrunch: https://techcrunch.com/2026/11/16/openai-will-embed-apollo-researchers-to-investigate-ai-subversion/ (발표 2026-11-16T17:02:43.000Z)

작성: TUMN 큐레이션 · AI 보조: false
발행: 2026-11-16T17:02:43.000Z
확인: 2026-11-16T20:28:03.207Z
검토: 원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.
정식 URL: https://api.tumn.com/news/59aa4f2b-a942-48c3-829d-b7bc71318cac
