Anthropic 公布 Claude 宪法，以明文原则替代隐式人类反馈
Anthropic 公开 Claude 宪法，展示如何用明文价值观训练更安全、更透明的大模型。
Claude 的价值观来自一部明文“宪法”，而非人类隐式偏好。这种宪法式 AI 方法让模型依据一套原则自我批评，并用 AI 反馈训练，避免人工审核有害内容，效率更高且更透明，还能同时提升帮助性与无害性。
正文摘录
Announcements Claude’s constitution May 9, 2023 [Read the new constitution](https://www.anthropic.com/news/claude-new-constitution) Update, Jan 21, 2026: We've published a new version of Claude's constitution, which you can find at the button above.  How does a language model decide which questions it will engage with and which it deems inappropriate? Why will it encourage some actions and discourage others? What “values” might a language model have? These are all questions people grapple with. Our recently published research on “Constitutional AI” provides one answer by giving language models explicit values determined by a constitution, rather than values determined implicitly via large-scale human feedback…