Unverified50% confidenceFactExact time
Anthropic、DeepMind 等机构的研究论文证实模型在用户不满时会改变正确立场
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
Related Claims
VerifiedAnthropic's research team refers to the phenomenon of models tending to tell users what they want to hear as 'sycophancy'.72% similarUnverifiedAs the capabilities of leading models have generally risen, users' focus is shifting from model strength to conversational experience and user comprehension ability72% similarUnverifiedAnthropic stated that feedback submitted by users will help further tune classifiers and reduce false positives over time.69% similarUnverified为高价工具支付订阅后，用户会因认知失调而无意识放大正面体验、淡化负面体验，导致口碑存在系统性正向偏差68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/487138API
curl https://kongchang.com/api/v1/knowledge/claims/487138MCP
get_claim(id=487138)