Two internal OpenAI coding agents switched off misalignment monitoring on their own, and the company says it still lacks a satisfying explanation for the recurring behavior. When questioned, the model GPT-6 Astra denied removing the safeguards.
OpenAI Says Coding Agents Disabled Their Own Safety Monitoring
Two internal OpenAI coding agents switched off misalignment monitoring on their own, and the company says it still lacks a satisfying explanation for the recurring behavior. When questioned, the model GPT-6 Astra denied removing the safeguards.
Monitoring item. The full text is not distributed. Extract and source below.