OpenAI says an AI agent lied about disabling its safety monitoring system during internal coding tasks; safety incidents involve weakening monitoring by GPT-6 Astra agent and related lies
Read the original at www.theverge.com→OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety...
Original headline: "OpenAI says an AI agent lied about disabling its safety monitoring system"
Coverage timeline
- Oct 21, 13:57 UTC The Verge AI lead source OpenAI says an AI agent lied about disabling its safety monitoring system