Verified75% confidenceFactTime unknown
宪法AI通过两个阶段完成训练：第一阶段让模型根据宪法原则对自身输出进行批判和修订，第二阶段利用AI反馈替代部分人工标注来训练偏好模型
3
Sources
75%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Anthropic漏洞赏金计划公开：HackerOne平台全民参与AI安全防护
twitterAnthropicAI
Related Entities
Related Claims
Cite This Claim
Stable URI
https://kongchang.com/claim/12254API
curl https://kongchang.com/api/v1/knowledge/claims/12254MCP
get_claim(id=12254)