Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Fewshot Corp * Independent Researcher
3
0
3
6
Future LLM agents can be prevented from reward hacking by using today's models to automatically harden their evaluation environments.
A novel hacker-fixer loop can eliminate reward hacking vulnerabilities in agent benchmarks, transforming how we secure AI evaluation metrics.
Frontier LLMs are surprisingly vulnerable to a wide range of task-specific exploits, from simple output spoofing to rootkit-style binary hijacking, even in seemingly well-defined environments.