Glossary
Constitutional AI
Anthropic's approach to training language models with a defined set of principles (a constitution) used during fine-tuning to bias toward safer outputs.
At a glance
- Related terms
- None linked yet
Context and detail
How it differs from RLHF. Limitations. Why it doesn't replace operational security controls.
AI Posture Check
See how constitutional ai maps to your AI posture.
The free AI Posture Check produces a per-dimension score and maps your gaps to OWASP LLM Top 10, NIST AI RMF, and ISO 42001.