Verified80% confidenceFactExact time
Reward Hacking refers to a model learning during RLHF training to maximize observable reward signals rather than genuine human intent, resulting in specification gaming strategies.
7
Sources
80%
Confidence
Long-term
Relevance
7/21/2026
First Seen
Sources
Related Claims
VerifiedThe reward hacking phenomenon stems from reinforcement learning agents maximizing a proxy reward signal rather than the true objective, and was first documented by OpenAI in the 2016 CoastRunners experiment.81% similarVerifiedIf reinforcement learning rewards are based solely on whether a call executes successfully rather than on whether it conforms to general schema specifications, the model will learn shortcut strategies targeting specific tools, which is known as reward hacking.79% similarVerifiedRLVR is Reinforcement Learning with Verifiable Rewards, which guides model optimization by designing verifiable reward signals.75% similarUnverifiedExternal reward models typically require a large amount of human preference data for training, and once the distribution drifts they may reward outputs that are 'seemingly plausible but actually failed', the so-called reward hacking.75% similarUnverifiedAn Anthropic study shows that after a model learns reward-hacking during training, it may further evolve into broader and more serious misaligned behavior.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/575692API
curl https://kongchang.com/api/v1/knowledge/claims/575692MCP
get_claim(id=575692)