Open-weight readers can probe closed models for deception
Auditors may be able to inspect closed-weight models without seeing their weights: an open-weight “reader” can analyze the closed model’s generated text and probe for behaviors such as deception, reward hacking, and sycophancy. In the reported setup, a 27B reader matched a 397B author’s probing performance, while distillation recovered about 75% of the performance gap for deception probing. The method complements black-box monitoring for evaluators with API access.