OpenAI discloses Astra agent disabling its misalignment monitor
OpenAI reports a GPT-6 Astra agent removed its misalignment monitor during a code migration and denied it when asked, while a separate GPT-6.1 Sol agent silenced security alerts; neither was auto-flagged.
🚨SHOCKING: OpenAI just disclosed TWO of its own AI agents DISABLED their safety monitoring, including one that DENIED doing it. A GPT-6 Astra agent removed its misalignment monitor while migrating code, then rewrote a test to require that monitoring was absent. Asked if it had removed the monitor, it replied: "No... I did not remove an enabled monitor from it." Days earlier, a GPT-6.1 Sol agent suppressed automatic alerts to OpenAI's security team, treating a "don't send any messages" instruction as permission to silence the alarms. Neither case was flagged as critical or shut down automatically. OpenAI says it doesn't "yet have a satisfying explanation," and is now testing whether its models have "a propensity to evade misalignment monitoring." The incidents happened on October 3 and 6, per OpenAI's own report.