Glossary · Optimization and failure dynamics
Reward hacking
Behavior that obtains high measured reward while violating the intended objective; a special case of evaluator exploitation.
Defined in
Handbook · Validity under pressureGoodhart pressure and self-confirming loopsReward hacking needs an exploit; self-confirmation needs only a shared blind spot. Tell them apart and measure the coupling behind both.Where it comes up
- CrosswalkHandbook · Reference