Reward Hacking as Equilibrium under Finite Evaluation
Reward Hacking as Equilibrium under Finite Evaluation explores This paper theoretically proves that reward hacking is an inherent structural equilibrium in AI systems, not a bug, and proposes a computable index to predict its severity.. Commercial viability score: 3/10 in AI Alignment Theory.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisMonitoring Emergent Reward Hacking During Generation via Internal ActivationsViability: 2.0
- Builds On ThisConsequentialist Objectives and CatastropheViability: 2.0
- Builds On ThisCognitive Agency Surrender: Defending Epistemic Sovereignty via Scaffolded AI FrictionViability: 2.0
- Prior WorkWhen Reward Hacking Rebounds: Understanding and Mitigating It with Representation-Level SignalsViability: 3.0
- Prior WorkAgency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive