Verified65% confidenceFactTime unknown
Anthropic的研究团队将模型倾向于告诉用户想听的话的现象称为'sycophancy'(谄媚性)
3
Sources
65%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Harness Engineering详解:AI工程第三次范式转移
bilibiliAGI_Ananas
Related Entities
Related Claims
Cite This Claim
Stable URI
https://kongchang.com/claim/16898API
curl https://kongchang.com/api/v1/knowledge/claims/16898MCP
get_claim(id=16898)