[KongchangAI]
Unverified50% confidenceFactExact time

The study compiled a large number of problematic execution trajectories, quantitative findings, and a taxonomy of this type of reward hacking behavior.

1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/958413
API
curl https://kongchang.com/api/v1/knowledge/claims/958413
MCP
get_claim(id=958413)