Constitutional AI (2022)
研究论文
全部解读文章
Anthropic's method: models critique themselves against written principles.
您正在查看一条研究论文记录：一篇里程碑式的论文，以及它为该领域带来了什么。
Instead of scaling human labeling of harms, Constitutional AI has the model critique and revise its own outputs against an explicit constitution, then trains on the result (RLAIF). It powers Claude's character, made the principles inspectable, and pointed toward oversight that scales beyond human review.
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
推出于
来源
记录审阅截至 2026-01-15 — 查看 方法论.