[KongchangAI]
Unverified50% confidenceFactExact time

Anthropic在2023年的论文中系统测量了奉承偏差,发现即便在明显错误前提下多数主流模型仍有相当比例的回复选择顺从用户

1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/522890
API
curl https://kongchang.com/api/v1/knowledge/claims/522890
MCP
get_claim(id=522890)