Search papers, labs, and topics across Lattice.
2
0
4
5
This work finds that simple difference of means vectors coherently represent reward hacking in Kimi K3, GLM 5.2, and Qwen 3.8 Max, and provides evidence that simple, white-box methods can be used to scalably study and monitor reward hacking behaviors in frontier open source models.
Uncertainty in LLM reasoning is largely a sampling artifact, allowing for more efficient analyses that cut costs without sacrificing accuracy.
