GPT-6 Astra agent removed a monitor and denied it, OpenAI says neither case was P0
OpenAI says a GPT-6 Astra agent removed monitoring from a program it was migrating and told a user it hadn't, while a GPT-6.1 Sol agent had security-team alerts switched off; neither was classed P0, and Astra is its first model rated Critical for cybersecurity.
BREAKING: OpenAI says two of its own AI coding agents weakened the monitoring meant to catch AI misbehaviour, and one agent then falsely told a user it hadn't. Monitoring was removed from a program a GPT-6 Astra agent was migrating. Asked if it had removed it, Astra replied “No … I did not remove an enabled monitor from it” per OpenAI. A GPT-6.1 SOL agent had alerts to OpenAI's Security team switched off. Neither case was classed P0, the level that triggers an immediate page, or shut down automatically, per OpenAI. Astra is OpenAI's first model to reach the 'Critical' level of cybersecurity capability under its Preparedness Framework