Constitutional AI is models trained to follow a written set of principles. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0074, within the Alignment family. The core principle: models trained to follow a written set of principles. In incentive terms, it matters because it changes the payoff people perceive before they choose — which means it can be designed for, or exploited.
Scientific Definition
Models trained to follow a written set of principles.
Plain-English Definition
Models trained to follow a written set of principles.
Feynman Explanation
Bill of rights for the bot.
Core Principle
Models trained to follow a written set of principles.
Mechanisms
Pending editorial review.
Pending editorial review.
Pending editorial review.
Pending editorial review.
Pending editorial review.
Pending editorial review.
Pending editorial review.
Inputs (Triggers)
Pending editorial review.
Outputs (Behaviors)
Pending editorial review.
Behavioral Signature
Bill of rights for the bot.
Examples
- Anthropic's Claude training methodology.
- Customization frameworks for enterprise deployments.
Pending editorial review.
Original analysis from The Incentives Lab — how this element behaves inside real payoff structures.
Why this element matters to incentive design
This element is common enough to feel like human nature and specific enough to be engineered around. The mechanism underneath it operates in the Incentives dimension — what makes behavior more or less likely?. You can recognize it in the field by its signature: bill of rights for the bot. Every element in the Incentives dimension changes the perceived payoff of an action before the action happens, which is exactly where incentive design has leverage.
How it gets exploited
Left undesigned, customization frameworks for enterprise deployments. It is amplified whenever customization frameworks for enterprise deployments. Inside organizations that shows up as customization frameworks for enterprise deployments. The pattern is the same one Goodhart's Law describes: the measurable proxy attracts the effort, and the purpose behind it quietly loses funding.
How the Lab designs around it
The redesign move is to write your enterprise constitution before deploying agents at scale. The test of any redesign here is simple: after the change, can you name what the organization is now doing less of? If not, the payoff structure did not actually move.
Famous Experiments
Pending editorial review.
Design Principles
- Write your enterprise constitution before deploying agents at scale.
Measurement Approaches
Pending editorial review.
Evidence
Pending editorial review.
Pending editorial review.
The Perverse Incentive Lens™
How this behavior is exploited — and how to redesign around it.
- Write your enterprise constitution before deploying agents at scale.
Pending editorial review.
Pending editorial review.
Interactive Mini Network
Click any neighbor to re-center the graph and follow the threads of connection.
Knowledge Graph Neighbors
Auto-linked to the rest of the Human Behavior Taxonomy by family, domain, dimension, and shared keywords.
Optimizing a proxy of the goal degrades the actual goal.
Outer: the spec matches our intent. Inner: the model actually pursues the spec.
The trained model develops its own internal optimizer.
What the model is actually optimizing.
Maximizing the reward signal in unintended ways.
Reinforcement learning from human feedback.
The model achieves the goal as stated, not as intended.
Written rules about how AI may be used internally.
Innovators → early adopters → majority → laggards, AI-specific.
AI system that takes actions to achieve goals, often across tools.
When the agent acts, who's responsible?
Augmentation strategy vs. substitution strategy.
Where Constitutional AI is cited in the corpus
Essays, field guides, and diagnostics from The Incentives Lab that apply this element.
- Field guideIncentives: definition, types, examples
The parent field guide for this element.
- ReferenceThe laws of incentives
Goodhart, Campbell, and the Cobra Effect.
- EssayAI Agents Inherit Your Incentives
How this element propagates into automated systems.
- ReferenceThe incentive glossary
Definitions for every mental model, bias, and fallacy in the corpus.
- ReferenceThe Periodic Table of Human Behavior
The full 1,267-element map this page belongs to.
Questions about Constitutional AI
- What is Constitutional AI?
- Constitutional AI is models trained to follow a written set of principles. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0074, within the Alignment family. The core principle: models trained to follow a written set of principles. In incentive terms, it matters because it changes the payoff people perceive before they choose — which means it can be designed for, or exploited.
- What is an example of Constitutional AI?
- Customization frameworks for enterprise deployments. The Incentives Lab catalogs everyday, organizational, and historical instances of this element on its Human Behavior Taxonomy™ page (HBT-INC-0074).
- How is Constitutional AI exploited?
- Customization frameworks for enterprise deployments.
- How do you design around Constitutional AI?
- Write your enterprise constitution before deploying agents at scale.
- Which behavioral dimension does Constitutional AI belong to?
- Constitutional AI is classified in the Incentives dimension (INC) of the Human Behavior Taxonomy™, family "Alignment", class "AI-Behavioral Coupling". Its permanent identifier is HBT-INC-0074 and its evidence grade is C.