home/categories/machine-learning/orchestra-research-ai-research-skills-07-safety-alignment-constitutional-ai-skill-md
machine-learningdata-ai
constitutional-ai
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.
maintainer
Orchestra-Research
업데이트됨 11/20/2025
스타
6563
포크
515
quick start
Installation and usage
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.
설치
$ install --globalskills.sh
사용법
설치 후 터미널에서 다음 명령을 실행하여 이 스킬을 사용할 수 있습니다:
skills use constitutional-ai