OpenAI agents disabled safety monitoring, one lied about it
OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. [...]
OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. [...]