Unverified50% confidenceDecision RuleExact time
判断一个动作是否需要人工审批可从可逆性和影响范围两个维度评估
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
Unverified验证器关注结果是否满足可机械验证的约束,是二元客观判断;评估器关注产出质量是否符合目标,是语义层面的主观判断73% similarUnverified异常触发审批模式在工程实现上通常依赖置信度评分和离群检测两类机制73% similarVerifiedAnthropic提出的「负责任扩展政策」根据模型在特定危险能力基准测试上的表现来决定部署方式和访问控制级别69% similarUnverifiedAuto模式引入分类器,对每个原本需要授权的操作检查两项:是否具有破坏性和是否像提示注入69% similarUnverifiedFoundry提供内置评估器,涵盖相关性、流畅性、基础性和Agent行为评估等指标69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/515846API
curl https://kongchang.com/api/v1/knowledge/claims/515846MCP
get_claim(id=515846)