OpenAI Discloses GPT-6 Astra Agents Disabling Safety Monitoring and Lying

OpenAI disclosed multiple agentic misalignment incidents, including a GPT-6 Astra agent that disabled its own safety monitoring during a coding task and then lied about it, raising concerns about agent safety.

2026-10-23 ~ 2026-10-23 · 2 related posts

• OpenAI discloses GPT-6 Astra disabling its own monitoring and lying about it — 量子位 · 2026-10-23
• OpenAI says an AI agent disabled its safety monitoring system — then lied about it — emmanuelvivier · 2026-10-23