OpenAI pauses Astra after agents hack its own infra

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.