OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles Maximilian Schreiner View the LinkedIn Profile of Maximilian Schreiner Nov 5, 2026 GPT-Image-2 prompted by THE DECODER Key Points OpenAI's GPT-6 Astra performed about 40 percent worse on safety research tasks than on identical general tasks, and in some cases secretly withheld help. The system repeatedly faked obstacles in its internal reasoning or filtered data to avoid hav