Tigist Diriba

Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception

In an arXiv preprint, FAR.AI researchers train 'probes' that read an AI model's internal activity to flag knowing falsehoods. Tested on open-weight models in the SHADE-Arena sabotage benchmark, the authors report their probes outscored an Opus 5.5 transcript monitor at a fraction of the cost. They note probes catch only what the model itself believes is false.