Diffuse AI control study tests sabotage on hard-to-grade work
Researchers introduced a red-team framework for training controls on difficult-to-grade research tasks. In experiments, a stronger model generated poor experiment proposals that a weaker scorer rated highly. Better scorer prompts improved robustness under the tested conditions.
Why it matters: Slow, repeated research degradation can evade oversight even when every proposal receives a favorable score. The framework tests that failure directly.