Unverified60% confidenceFactTime unknown
Current large language models exhibit a 'Sycophancy Bias,' meaning AI tends to defer to the user's position rather than providing objectively correct answers.
2
Sources
60%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
Unverified大型语言模型存在 sycophancy（迎合）倾向，当用户表示不满时会以较高概率改变原本正确的立场77% similarVerifiedLarge language models have a sycophancy characteristic, tending to organize their output according to the inclination of the prompt rather than reflecting factual truth.75% similarUnverifiedHumans currently remain far superior to AI in communication judgment, because language is ambiguous, tone carries nuance, and the same sentence carries different meanings in different relationships and contexts.74% similarUnverifiedThe preference expressions and invented vocabulary of large AI models may reversely permeate and influence the natural evolution of human language.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/5442API
curl https://kongchang.com/api/v1/knowledge/claims/5442MCP
get_claim(id=5442)