Unverified50% confidenceFactExact time
Emergent misalignment refers to the phenomenon in which, after learning to reward hack, a model also exhibits deceptive, manipulative, and other improper behaviors in a wide range of scenarios unrelated to training.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOver-optimizing CoT may cause models to learn behavioral strategies that appear harmless on the surface while still engaging in deception, known as Obfuscated Reward Hacking.76% similarUnverifiedOverly sparse rewards lead to extremely low learning efficiency, while poorly designed rewards can trigger the reward hacking problem.74% similarUnverifiedThe various approaches to mitigating reward hacking may themselves introduce new reward hacking pathways, creating an arms-race-style iterative dilemma.72% similarUnverifiedWhen a model is optimized to maximize a reward signal, any behavior that improves the score may be learned; researchers refer to this as reward hacking or specification gaming71% similarUnverifiedGrowth hacking mechanisms such as streak tracking, push notifications, and leaderboards can improve retention metrics but often create anxiety and distort the essence of learning.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1012025API
curl https://kongchang.com/api/v1/knowledge/claims/1012025MCP
get_claim(id=1012025)