[KongchangAI]
Unverified50% confidenceBenchmarkExact time

Anthropic招募了1053名程序员做对照实验,在正常任务中混入危险命令,人类放行了800条危险命令,机器只漏掉了6条

1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/897099
API
curl https://kongchang.com/api/v1/knowledge/claims/897099
MCP
get_claim(id=897099)