---
id: "2022-12-15-constitutional-ai"
url: "https://postcutoff.com/e/2022-12-15-constitutional-ai/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2022-12-15"
date_precision: day
category: policy-safety
importance: 4
confidence: high
status: [Confirmed]
sources: 2
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2022-12-15-constitutional-ai/

# Anthropic introduces Constitutional AI (RLAIF)

Anthropic's Constitutional AI trained a harmless-but-helpful assistant using AI feedback guided by a written set of principles (a 'constitution') instead of human harm labels.

## Key facts
- arXiv 2212.08073 'Constitutional AI: Harmlessness from AI Feedback' (December 2022)
- Two phases: supervised self-critique and revision, then RL from AI feedback (RLAIF)
- Used in training Anthropic's Claude models
- Anthropic published Claude's constitution in May 2023

## What happened

The model critiqued and revised its own outputs according to principles, and a preference model trained on AI judgments then guided RL.

## Why it matters

Showed alignment could scale with AI supervision, making values explicit and auditable; RLAIF is now widespread.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Constitutional AI: Harmlessness from AI Feedback (Anthropic)](https://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback) (anthropic.com, official)
2. [Constitutional AI (arXiv)](https://arxiv.org/abs/2212.08073) (arxiv.org, paper)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2023-03-14: [Anthropic releases Claude](https://postcutoff.com/e/2023-03-14-claude-1/index.md)
- 2022-01-27: [InstructGPT: RLHF aligns language models to follow instructions](https://postcutoff.com/e/2022-01-27-instructgpt/index.md)