Simple model probes catch reward hacking before actions happen
A cheap internal monitor can flag reward hacking in open-source LLMs before the model takes the suspicious action, giving evaluation teams an alternative to expensive LLM-based detectors. The method uses difference-of-means vectors, which compare internal representations of hacking and non-hacking behavior, and can run on chain-of-thought online. On DeepSWE, it caught 3.1% more hacks in Kimi K3 and 7.9% fewer in GLM 5.2 than an LLM monitor at the same false-positive rate.