Expired50% confidenceFactTime unknown
Academia refers to the phenomenon of models preferring to fabricate rather than admit ignorance as 'sycophancy'.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
How Multi-Agent Teams Solve AI Hallucination and Make AI Reliable
bilibilililiMozi
Related Claims
Unverified该研究关注模型在自然日常推理任务中自发出现的不忠实现象（in the wild），而非人为构造的对抗性提示69% similarUnverifiedLarge models are prone to 'hallucination' when handling professional domain questions, meaning they confidently provide incorrect answers.68% similarUnverified教育心理学中的「专家盲点」现象说明领域专家因知识过度内化，难以还原初学者的困惑路径67% similarUnverifiedThe normalization discrepancy in the paper was severe enough that one conclusion appeared to directly contradict a known theorem.67% similarUnverifiedWhen a model lacks accurate knowledge of a particular library, it tends to generate syntactically correct but semantically incorrect code—so-called 'confident errors.'66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/58368API
curl https://kongchang.com/api/v1/knowledge/claims/58368MCP
get_claim(id=58368)