/constitutional-ai
Anthropic 透過自我改進訓練無害 AI 的方法,分兩階段:自我批評與修正的監督式學習,再做 RLAIF。用於安全對齊,不靠人工標註減少有害輸出。
- 安裝次數
- 971
- 專案星數
- 1.4 萬 ★
- 授權
- MIT
- 專案更新
- 2026-10-11
怎麼裝
npx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs --skill constitutional-ai安裝前請先看過原文內容。中文說明是 AI 翻譯,不保證安全。
原文
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.