Installs as a private draft. Your edits and self-improvement runs do not change the published bundle.
Self-critique and revision loops using model-generated feedback
Self-critique and revision loops using model-generated feedback
Anthropic's approach; reduces human annotation needs
RL Training Infrastructure > RL Algorithm Implementation
--- name: "Implement Constitutional Ai" version: "1.0.0" description: "Self-critique and revision loops using model-generated feedback" tags: - rl-skills-universe - "rl-training-infrastructure" - "rl-algorithm-implementation" trigger: "implement-constitutional-ai" --- # Implement Constitutional Ai Self-critique and revision loops using model-generated feedback ## Why It Matters Anthropic's approach; reduces human annotation needs ## Domain **RL Training Infrastructure** > RL Algorithm Implementation