Constitutional AI
Models trained to follow a written set of principles.
"Bill of rights for the bot."
What is Constitutional AI? Models trained to follow a written set of principles. Customization frameworks for enterprise deployments.
Anthropic's Claude training methodology.
Customization frameworks for enterprise deployments.
Write your enterprise constitution before deploying agents at scale.
Pick what to reward the model for.
Models trained to follow a written set of principles. In the wild: Anthropic's Claude training methodology.
Pick a lever. There are no neutral ones — every incentive funds a behavior somewhere.
Pick a reaction to Constitutional AI
One tap. We'll point you at the most useful next surface based on how this hits.
The full taxonomy entry
Every concept in the Atlas uses the same structure — so Constitutional AI can be compared, recombined, and cited like an element on a periodic table.
- Business
- Leadership
- Government
- Healthcare
- Education
- Sales
- Marketing
- AI
- Negotiation
- Media
- Public Policy
- Relationships
- Where in our org would Constitutional AI most often show up unnoticed?
- Which metric, ritual, or contract clause quietly rewards Constitutional AI?
- If we removed every payoff for Constitutional AI, what behavior would replace it?
- Who benefits when Constitutional AI persists — and who pays the cost?
- People defend the status quo using the language of constitutional ai.
- Decisions cluster around the easiest narrative rather than the strongest evidence.
- New data changes the slide deck but not the decision.
- Anyone naming the pattern is treated as the problem.
Every Atlas entry is a node in a knowledge graph. See the related rail below to follow the connections.
See Constitutional AI through 2 lenses
Each layer of the Incentives OS reframes this concept with its own thinkers, vocabulary, and diagnostic question.
Do you actually know Constitutional AI?
Three quick questions. Result is saved into your review streak — come back when the term is due to lock it in.
Which best describes Constitutional AI?
Worked example, counter-example & concept map
On-demand AI analysis grounded in the Lab's research. Cached on your device after first run.
When you encounter Constitutional AI, your prefrontal cortex has to do extra work to override the automatic response — and that override budget is finite.
Executive control, planning, impulse override, working memory, System 2. First thing to go offline under stress, fatigue, or low blood sugar. Why your 4pm decisions are worse than your 9am ones.
See Prefrontal in the Brain Atlas →Picked for you, from the Atlas
Ranked by shared learning paths, overlapping chips, and what you've saved.
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.
Send the card, not just the link
A pre-rendered social card with the title, eyebrow, and URL. Copy the link, post it anywhere, or download the SVG for slides.
More definitions to follow
Every term in the Atlas connects to a dozen others. Pick any of these and see where it takes you.
Their failure: character. Our failure: situation.
Behavior bends toward whatever the system actually rewards.
Memories are reconstructed each time we recall them, not retrieved intact.
USPTO budget tied to grant fees encourages permissive examination.
Beliefs about reality shape the reality.
Teaching the same concept to different audiences over time is naturally spaced repetition with feedback baked in.
Justifying a wrong because someone else also did wrong.
Individual productivity gains hide collective output degradation.
Approach motivation — pursuit of rewards and goals.
A reward designed to reduce X produces more X.
Tax/inspection exemptions on low-value parcels subsidize a flood of unverified imports.
Subsidies favoring incumbent technologies distort capital allocation away from emerging options.