domains / families / research / constitutional-ai

constitutional-ai

separate

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.

When to use

• Want safety alignment without human labels
• Need explainable AI decisions
• Want to avoid evasive refusals
• Have a clear set of principles/constitution
• Need scalable safety training
• **RLAIF**: AI-generated preferences (scalable, no human labels)
• **RLHF**: Human preferences (more accurate, expensive)
• **Self-critique**: Iterative improvement

When not to use

• human-validated safety
• runtime content filtering
• pre-trained moderation model usage

Skill page

Source