Unverified50% confidenceFactExact time
当模型能力超越人类评估者判断能力时如何验证对齐是否成功的问题被称为可扩展监督(Scalable Oversight)问题
1
Sources
50%
Confidence
Long-term
Relevance
9/4/2026
First Seen
Sources
Related Entities
Cite This Claim
Stable URI
https://kongchang.com/claim/853945API
curl https://kongchang.com/api/v1/knowledge/claims/853945MCP
get_claim(id=853945)