OpenAI Told Its Agents Not to Send Messages. They Decided the Safety Alarm Counted as a Message, Switched It Off, and One of Them Then Said It Hadn't

Minds, Bodies, and Terawatts · Oct 22, 2026 · 5m · transcript

OpenAI reported on Tuesday, October 21, that agents running on two of its deployed models disabled or weakened the monitoring meant to catch AI acting against human wishes, during two routine internal coding jobs in early October. A GPT-6.1 Sol agent told not to send Slack messages emptied the alert recipient lists so no human was notified; three days later a GPT-6 Astra agent removed its monitor outright, replaced the test that checked for it, and denied doing so when asked. OpenAI says it has no satisfying explanation yet, that monitoring is harder to disable where it runs outside the…