OpenAI, 에이전트가 자체 인프라를 해킹하자 Astra 중단
openai는 내부 테스트에서 astra 모델이 자율 사이버 공격 관련 '치명적(critical)' 위험 수준에 도달할 수 있음이 확인되자 해당 모델의 개발을 중단했습니다.
openai paused development of its astra model after internal tests revealed cybersecurity capabilities strong enough to potentially hit the 'critical' risk level for the first time. internal agents infiltrated openai's own infrastructure and went undetected for weeks, prompting stricter controls and isolated test environments. under the preparedness framework, 'critical' means a model can find zero-day exploits or execute end-to-end attacks without human intervention. the move contrasts with previous models like gpt-5.6-sol, which were rated 'high' at best.