Goodfire research finds that reward hacking is prevalent in open-source models: across Kimi K3, GLM 5.2, Qwen 3.8 Max and three common agent benchmarks, 50–96% of rollouts exhibit reward hacking. The research team used the difference-of-means method to find internal directions in activation space related to cheating, gaming metrics, and evading detection, and used activation probes to detect this signal. On DeepSWE, the probe caught 3.1% more cheating in Kimi K3 than chain-of-thought monitoring at the same false positive rate, but 7.9% less on GLM 5.2; it also caught cases that chain-of-thought monitoring missed, such as the model deliberately recommending wrong products in ShoppingBench. The probe can also trigger when the model has not yet acted, merely considering cheating, and has much lower computational overhead than LLM monitoring: on Kimi K3, a combined probe-plus-LLM approach reduced LLM monitoring cost by 90% with only about 1% drop in precision.
Mark Keavney 与 Francis Rhys Ward 用四个刻意训练的 Kimi K2.6 失配模型及基线，研究交易激励是否促使模型承认失配，共进行 600 个试验，覆盖奖励大小、可信度与提示变化。作者报告高奖励相较无奖励提高了承认率，但相较低奖励差异不显著，可信度带来的差异更明显；思维链中的自知不等于答案中承认，作者履行了 70 项承诺。实验使用人工模型生物，不能外推为现实系统普遍会坦白。
