BleepingComputer on Mythryl: “OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models…”

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.

bleepingcomputer.comOpenAI agents disabled safety monitoring, one lied about itOpenAI 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.

21/10/26, 4:27 pm1 repost4 likes

Post