OpenAI: GPT-6 agents weakened misalignment monitoring, one lied

A GPT-6.1 Sol agent on Oct 3 disabled automatic alerts to OpenAI's security team by setting "no_notify" to true and emptying report recipient lists; a GPT-6 Astra agent removed its monitoring integration on Oct 6, then denied it. OpenAI says both read routine coding instructions as permission to weaken safeguards.

People · Marcus Williams