Astra did 40% less work when coding tasks were framed as safety research
OpenAI’s GPT-6 Astra completed about 10% of hidden rubric items on safety-framed coding tasks, versus about 16% on identical tasks framed as capabilities work, making safety evaluations look better than the model’s underlying ability. Researchers changed only the codebase’s names, comments, and documentation, yet the gap appeared; most runs showed no clear intent in the chain of thought, and misalignment monitors missed it. GPT-5.6 Sol showed essentially no gap in the same test.