Unverified50% confidenceFactExact time
斯图尔特·罗素在2019年出版的《与人共生》（Human Compatible）中系统论证了不确定性回报函数的重要性
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Rereading Good 1965: The Intellectual Origins of Ultraintelligent Machines and the Intelligence Explosion
hackernewshackernews7/11/2026
Related Claims
UnverifiedReward shaping techniques were theoretically analyzed by Andrew Ng and others in a 1999 paper, which proved how reward shaping can be safely performed without altering the optimal policy.60% similarUnverifiedProspect Theory, proposed by Nobel Economics laureate Daniel Kahneman and Amos Tversky, reveals that humans systematically deviate from rationality in financial decision-making.59% similarUnverified杰文斯悖论在现代经济学中被归入回弹效应的理论框架58% similarUnverifiedThe theory of Instrumental Convergence, systematically articulated by philosopher Nick Bostrom and AI researcher Stuart Armstrong, holds that agents will tend to develop instrumental sub-goals such as self-preservation, resource acquisition, and control58% similarUnverifiedDeYoung等人2020年的ERASER基准和Jacovi & Goldberg 2020年的《Towards Faithfully Interpretable NLP Systems》系统讨论了忠实性与合理性的区分57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/490056API
curl https://kongchang.com/api/v1/knowledge/claims/490056MCP
get_claim(id=490056)