Glossary · Term

constitutional AI

← all terms

Definition

Plain language

A way to train an AI to behave using a written list of principles that another AI checks its answers against, instead of paying humans to label everything.

As stated in the literature

A training and oversight approach using an explicit written constitution plus a model-based judge to score and refine responses, scaling alignment supervision beyond human labeling; the basis for Self-CTRL's consistency experiments.

Also called: Constitutional AI

Why it matters: It scales safe behavior using written principles and an automated judge, instead of relying on humans to hand-label every response.

For example, a model's draft reply is checked by another AI against a written rule like 'don't give instructions for harm,' and rewritten if it breaks one.

Heard on the show

“… It's that an entire generation of safety methods — Constitutional AI, OpenAI's deliberative alignment — is built on the opposite assumption: that if you train a …”
Episode 171 — The Safety Decision a Model Makes Before It Thinks a Word

Mentioned in 3 episodes

  1. 171
    The Safety Decision a Model Makes Before It Thinks a Word
  2. 152
    Training a Model to Mean What It Says, And Why That Isn't the Same as Being Good
  3. 062
    Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety

Related concepts

Related terms