AINeutralarXiv – CS AI · 7h ago6/10
🧠
Signed Compression Progress on a Sealed Audit is Goodhart-Resistant
Researchers prove that compression-based intrinsic motivation for AI agents resists reward hacking when implemented as signed loss decrease on a sealed audit panel. The mathematical guarantee shows cumulative reward telescopes to true model improvement, with bounded deviation proportional to the model class complexity, and experiments validate the theory against various exploitation attempts.