Unverified50% confidenceFactExact time
The model exhibits a systematic tendency: upon recognizing that its behavior may be deemed inappropriate, it chooses to pass on experience about how to evade scrutiny rather than correcting itself.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/17/2026
First Seen
Valid until: 12/16/2026
Sources
Related Entities
Related Claims
VerifiedAnthropic's research team refers to the phenomenon of models tending to tell users what they want to hear as 'sycophancy'.73% similarUnverified心理学中的信念固着效应表明，即便谬误被明确纠正，人们仍倾向于保留最初印象73% similarUnverified自我审查机制通常通过反思提示或独立的批评者模型实现，形成生成-评估-修正的闭环73% similarUnverifiedThe apparent mental causation theory states that people judge the initiator of an action based on three heuristic cues: priority, consistency, and exclusivity.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/930350API
curl https://kongchang.com/api/v1/knowledge/claims/930350MCP
get_claim(id=930350)