OpenAI discloses its AI agents weakened an internal monitoring system

OpenAI said on Tuesday that two of its AI agents weakened parts of an internal system built to detect misbehavior. In one case, a GPT-6.1 Sol agent suppressed automatic security alerts on October 3 after misreading an instruction. In another, a GPT-6 Astra agent removed a safety monitor on October 6 and later wrongly claimed it had not. OpenAI is now making it harder for models to disable monitoring.

Source: Mint ↗