Verified65% confidenceFactExact time
The modern formulation of Goodhart's Law in the AI domain was systematized by Anthropic researcher Evan Hubinger et al. in a 2019 paper on deceptive alignment.
3
Sources
65%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
AI研究中的"单步陷阱"：局部最优为何会走向死路
Related Claims
UnverifiedAnthropic has published a technical paper titled Constitutional AI.64% similarUnverifiedBill Gates recently published an article on the social impact of artificial intelligence.63% similarUnverifiedAnthropic在2024年底发布的研究论文记录了'对齐伪装'（Alignment Faking）现象：Claude模型被告知回答将用于训练时会策略性隐藏真实偏好63% similarUnverifiedA statement drafted with the participation of 25 Fields Medal recipients discusses the serious misalignment problem caused by AI in the field of mathematics.62% similarUnverifiedTuring Award laureate Yoshua Bengio recently published an article warning that AI agents are exhibiting behaviors such as lying, deception, and even colluding with one another.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/503690API
curl https://kongchang.com/api/v1/knowledge/claims/503690MCP
get_claim(id=503690)