Glossary

Constitutional AI

What is Constitutional AI?

Constitutional AI is a training method for language models published by Anthropic in 2022; it has nothing to do with constitutional law. It is based on a written set of principles, the “constitution”: the model critiques and revises its own answers against these principles, then an AI compares pairs of answers, and this feedback serves as the reward signal for reinforcement learning (RLAIF). This reduces the need for human labelling of harmful content; in January 2026 Anthropic published a revised constitution for Claude.

How KI.ordo helps

The Anthropic Claude models used in KI.ordo are trained using this method, among others.

Topics

Training
AI safety
Anthropic

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

Reinforcement learning from human feedback (RLHF)

RLHF is a training method that makes language models more helpful and safer. People compare and rate several of the model's answers; these judgements are used to train a reward model, which then further trains the language model itself through reinforcement learning. This teaches it, for instance, to answer more clearly or to decline problematic requests. RLHF takes place at the model provider before a model is released – not with individual users.

training
human feedback
+1

Claude

Claude is a family of large language models from the US AI company Anthropic. The models understand and write text in many languages, analyse documents, write code and can use tools, for example for research or automation. Best known are the model families Haiku, Sonnet and Opus, which differ in speed, cost and capability. Anthropic places particular emphasis on safety and reliable model behaviour.

Anthropic
language model
+1

AI Ethics

AI ethics deals with the moral questions surrounding the development and use of AI: fairness and discrimination, transparency and explainability, data protection, responsibility for errors, safety and the effects on work and society. For organisations it becomes concrete in guidelines, risk assessments, human oversight and honest communication about AI's limitations. Example: before a CV screening tool is introduced, it is checked for whether it disadvantages particular groups.

Ethics
Responsibility
+1

LLM security

LLM security covers all measures that protect applications built on large language models from misuse, data leakage and unwanted behaviour. Typical risks include prompt injection, disclosure of confidential instructions or data, and agents with excessive permissions. Protection comes from several layers: clear instructions, restricted rights, checks on inputs and outputs, AI firewalls, red teaming and regular audits.

security
language models
+1

Template