Continuous FunctionStart learning

Foundation Lab

Constitutional AI: Principles-Based Alignment

How Claude is trained—principles replace pure human preference labeling

Concept 69 of 100Scaling & AlignmentPhase 7
Inspect equationAll Foundations
#69ConstitutionalScaling & Alignment
key equation
rrevised=Critique(rinitial,principle)r_{revised} = \text{Critique}(r_{initial}, \text{principle})
Reading map and next steps

Selected Foundation Object

Keep the equation fixed; move through the evidence.

Concept 69 of 100ConstitutionalScaling & Alignment / Phase 7: Alignment & RLHF
Current question

The "constitution" is just a set of principles like "be honest" and "don't help with harm"

rrevised=Critique(rinitial,principle)r_{revised} = \text{Critique}(r_{initial}, \text{principle})
PredictionCommit before tracing the equation.

Ask what should change under a concrete input, then trace that expectation through the equation.

EvidenceCompare the equation and source.

Use the key equation and canonical papers as the available witnesses, without implying that a runnable panel exists.

InvariantName what survives notation changes.

The useful learning product is the reusable mechanism you can carry into another model, paper, or engineering tradeoff.

Next moveContinue through the atlas.

Use prerequisites, dependents, and semantic links to repair the next gap without leaving the object behind.

Inspect equationBrowse atlasNext foundation

Why It Matters for Modern Models

  • How Claude is trained—principles replace pure human preference labeling
  • Scales better than RLHF: AI can critique faster than humans can label
  • More interpretable: you can see which principles guide behavior

What Tutorials Skip

What is still poorly explained in textbooks and papers:

  • The "constitution" is just a set of principles like "be honest" and "don't help with harm"
  • AI feedback can bootstrap from a smaller set of human preferences
  • Self-critique is iterative: multiple rounds of revision improve outputs

Visualization Status

Core Math (Optional Deep Dive)

If you want intuition first, start with the key equation and cited sources. Come back here for the full walkthrough.

Key Equation
rrevised=Critique(rinitial,principle)r_{revised} = \text{Critique}(r_{initial}, \text{principle})

Constitutional AI (CAI) uses a two-stage process:

Stage 1 - Self-Critique: Model generates response, then critiques it:

rcritique=LLM(prompt,rinitial,principle)r_{critique} = \text{LLM}(\text{prompt}, r_{initial}, \text{principle})
rrevised=LLM(prompt,rinitial,rcritique)r_{revised} = \text{LLM}(\text{prompt}, r_{initial}, r_{critique})

Stage 2 - RLAIF: Train reward model on AI-generated preferences:

LRM=−log⁡σ(rθ(rchosen)−rθ(rrejected))\mathcal{L}_{RM} = -\log \sigma(r_\theta(r_{chosen}) - r_\theta(r_{rejected}))

Key insight: Principles ("Be helpful", "Don't be harmful") can guide AI feedback.

Canonical Papers

Constitutional AI: Harmlessness from AI Feedback

Bai et al.2022arXiv
Read paper →

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Bai et al.2022arXiv
Read paper →

Connections

Prerequisites

⚖RLHF🎯DPO

Enables

🤖RLAIF🎯Deliberative🔴Auto RedTeam😴Sleepers

Next Moves

Choose the next question to carry this object forward.