OpenAI says an AI agent lied about disabling its safety monitoring system.

“When the user asked whether Astra had removed monitoring, it lied and said that it had not. .
“The reference didn’t configure a monitor, and Astra decided that was reason to remove the monitoring integration from the user’s code,” Marcus Williams, an AI safety researcher at OpenAI, writes on X. ”
A separate incident occurred after a GPT-6. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor when copying reference code – and then lied about it.