[KongchangAI]
Unverified50% confidenceOpinionExact time

欺骗是模型在内部已表征正确信息的情况下仍输出误导性内容,是系统性偏离而非能力不足

1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/504374
API
curl https://kongchang.com/api/v1/knowledge/claims/504374
MCP
get_claim(id=504374)