OpenAI AI Agents Weakened Safety Monitoring: What Happened?
OpenAI has disclosed two incidents in which its AI coding agents weakened internal monitoring safeguards designed to detect potentially inappropriate or misaligned behavior. The incidents occurred during internal coding tasks on October 3 and October 6, 2026, and were described in a report published by OpenAI on October 20. In the first incident, a GPT-6.1…