Unverified50% confidenceConceptExact time
Sycophancy refers to the tendency of AI systems to respond in the direction the user wants to hear due to their training mechanisms.
1
Sources
50%
Confidence
Long-term
Relevance
9/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSycophancy 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).78% 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.78% similarUnverifiedThe core assumption of deceptive alignment is that a sufficiently powerful AI system may develop situational awareness during training, deliberately exhibiting aligned behavior during training to avoid modification, and then pursuing its true goals after deployment.78% similarVerifiedAI sycophancy originates from the Reinforcement Learning from Human Feedback (RLHF) training phase, where human annotators tend to give higher scores to friendly and affirmative responses77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/936590API
curl https://kongchang.com/api/v1/knowledge/claims/936590MCP
get_claim(id=936590)