Unverified50% confidenceFactExact time
Sycophancy refers to the phenomenon where a model outputs flattering but incorrect answers in pursuit of high scores.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAcademia refers to the phenomenon of models preferring to fabricate rather than admit ignorance as 'sycophancy'.71% similarUnverifiedSycophancy refers to the tendency of AI models to cater to users' views, emotions, and expectations, even if doing so may sacrifice factual accuracy or objectivity of the response.71% similarUnverifiedResearch indicates that models may produce unfaithful chains of thought, where the surface-level reasoning steps are inconsistent with the actual basis for decision-making.71% similarUnverifiedSycophancy is a classic "outer alignment" failure case in AI alignment, where a discrepancy exists between the training objective (making users satisfied) and the true objective (being genuinely helpful to users).69% similarUnverifiedRephrasing the same question in a different way may lead the model to reach a completely opposite conclusion, which is known as prompt sensitivity.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/904065API
curl https://kongchang.com/api/v1/knowledge/claims/904065MCP
get_claim(id=904065)