# Constitutional AI: Harmlessness from AI Feedback

Credited to: Yuntao Bai et al., Anthropic

Canonical: https://www.synapsebooks.app/catalog/constitutional-ai-harmlessness-from-ai-feedback

Status: Discovery record. No guide is published.

## Focus

Paper listed in Volume III under AI & Machine Learning.

## The Library, Volume III

Listed title: Constitutional AI: Harmlessness from AI Feedback

Listed credit: Yuntao Bai et al., Anthropic

Publication details: 2022

Source section: AI & Machine Learning

Source line: 448

Group: Consequential

Tags: free online

[Listed source](https://arxiv.org/abs/2212.08073)



Details and tags come from the supplied bibliography. Edition and access verification pending.

## Find the original

Edition verification pending. [Listed source](https://arxiv.org/abs/2212.08073)

This discovery record is not a book summary. Named editorial approval of guide text remains pending.
