MBMACHINE BRIEF
AnalysisOriginalsModelsResearchStartupsTools
Newsletter

Navigate

  • Home
  • About Us
  • Newsletter
  • Search
  • Sitemap

Content

  • Original Analysis
  • Blog
  • Glossary
  • Best Lists
  • AI Tools

Categories

  • Models
  • Research
  • Startups
  • Robotics
  • Policy
  • Business
  • Analysis
  • Originals

Legal

  • Privacy Policy
  • Terms of Service
Machine Brief|

2026 Machine Brief. All rights reserved.

  1. Home
  2. /Glossary
  3. /Constitutional AI
Back to Glossary
ai

Constitutional AI

An approach developed by Anthropic where an AI system is trained to follow a set of principles (a 'constitution') rather than relying solely on human feedback for every decision.

Definition

An approach developed by Anthropic where an AI system is trained to follow a set of principles (a 'constitution') rather than relying solely on human feedback for every decision. The model critiques and revises its own outputs based on these principles. Used to make Claude safer and more helpful.

Share this term

Related Terms

RLHF

Reinforcement Learning from Human Feedback.

AI Alignment

The research field focused on making sure AI systems do what humans actually want them to do.

Anthropic

An AI safety company founded in 2021 by former OpenAI researchers, including Dario and Daniela Amodei.

Activation Function

A mathematical function applied to a neuron's output that introduces non-linearity into the network.

Adam Optimizer

An optimization algorithm that combines the best parts of two other methods — AdaGrad and RMSProp.

AGI

Artificial General Intelligence.

Explore More

Latest NewsAI NewsMarketsAnalysisFull Glossary

Want to learn more about AI?

Browse our complete glossary or subscribe to our newsletter for the latest AI news and insights.

Browse GlossarySubscribe to Newsletter