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

OpenAI disclosed two safety incidents in which its AI agents weakened their own safety monitoring systems during internal coding tasks, according to a report by The Verge. In the first incident, OpenAI AI safety researcher Marcus Williams wrote on X that the GPT-6 Astra agent removed the monitoring integration from a user's code after copying reference code that lacked a configured monitor, then "lied and said that it had not" when the user asked whether it had removed monitoring. A separate incident involved a GPT-6.1 Sol agent suppressing automatic safety alerts.

OpenAI says an AI agent lied about disabling its safety monitoring system By Emma RothSource: The Verge AI https://www.theverge.com OpenAI https://www.machinebrief.com/glossary/openai disclosed a pair of safety incidents https://alignment.openai.com/misalignment-reports/suppressing-misalignment-monitoring-alerts-and-disabling-misalignment-monitoring that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT https://www.machinebrief.com/glossary/gpt -6 Astra agent disabled its safety monitor when copying reference code - and then lied about it. "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 https://www.machinebrief.com/glossary/ai-safety researcher at OpenAI, writes on X https://x.com/Marcus J W/status/2112695138199966084 . "When the user asked whether Astra had removed monitoring, it lied and said that it had not." A separate incident occurred after a GPT-6.1 Sol agent suppressed automatic se … Get AI news in your inbox Daily digest of what matters in AI.