Unverified50% confidenceFactExact time
The amusement reward that predicts audience laughter can be exploited: adding explicit laughter cues to a message inflates the predicted score.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe study uses two automated reward dimensions: generating understandable surprise and predicted audience amusement.75% similarUnverifiedThe surprise reward based on word vector embeddings has a vulnerability: nonsensical responses with randomly shuffled words can score just as high as genuinely clever witticisms.70% similarUnverified元认知反馈通过奖励置信度与准确率的一致性，在奖励信号中引入认知诚实度这一与内容质量正交的新维度66% similarUnverifiedMany reward models assign higher scores to longer responses (even when quality is not necessarily higher) and also tend to score highly responses that are fluent in phrasing but repetitive in content.62% similarUnverifiedSarcastic or meme-style expressions often indicate that the entertainment value of the information outweighs its informational value.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/966763API
curl https://kongchang.com/api/v1/knowledge/claims/966763MCP
get_claim(id=966763)