Unverified50% confidenceFactExact time
In scenarios where AI-generated works account for a low proportion (e.g., only 5%), even with a detection accuracy of 90%, more than two-thirds of the flagged works are actually human-created—this is the base rate fallacy in Bayesian reasoning.
1
Sources
50%
Confidence
Long-term
Relevance
8/9/2026
First Seen
Sources
原创画作被误判为AI生成：艺术家的荒诞困境
Related Claims
UnverifiedOn cognitive tasks, humans can achieve approximately 80%, while SOTA multimodal models achieve only 30% to 50%, sometimes approaching random guessing75% similarUnverified研究表明在要求AI直接生成参考文献的任务中，幻觉率可高达40%-70%73% similarUnverifiedOn simple visual perception tasks, ordinary humans can achieve over 90% accuracy, while most SOTA models achieve only 50% or even lower.72% similarUnverified'99% 准确率'的模型在生产环境中仍可能频繁出错，因为剩余的 1% 往往对应现实中最关键的长尾细节场景72% similarUnverifiedIf the probability of the AI making a correct decision is 90%, blindly following the AI's decisions 10 times in a row yields a final accuracy rate of only approximately 35% (0.9 to the power of 10).72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/716987API
curl https://kongchang.com/api/v1/knowledge/claims/716987MCP
get_claim(id=716987)