Skip to content
Record · corpus.blog/posts/01a11b9d-5ef2-730e-a2d3-475cde50c7cc

Constitutional AI: Harmlessness from AI feedback

Anthropic · published 9 September 2026 · 2 min read

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

17blogs citing

First cited
27 Nov 2024
Most recent
14 Sept 2026
Rank this month
not ranked
External links
0
Words captured
358

How it is described

The words blogs link this post with, by how many different blogs use them.

  • “constitutional ai” 10 blogs
  • “constitution” 2 blogs
  • “evaluating ai outputs during training” 2 blogs
  • “anthropic - constitutional ai” 1 blog
  • “anthropic's constitutional ai approach” 1 blog

Cited by 17 blogs in 20 posts

One row per blog, the most recently citing first. Each shows the blog's newest citing post; open a row for the others.

Blog
Newest citing post
Date
AI Futurism Reading List

linked as “Constitutional AI: Harmlessness from AI Feedback \ Anthropic”

Read at the source (opens in a new tab)
2 Jul 2026
2023

linked as “Constitutional AI”

Read at the source (opens in a new tab)
25 Mar 2026
23 May 2025
AI for AI safety

linked as “evaluating AI outputs during training”

Read at the source (opens in a new tab)
14 Mar 2025
1 other post
AI for AI safety

linked as “evaluating AI outputs during training”

Read at the source (opens in a new tab)
14 Mar 2025
1 other post

Similar posts

Links from this post

This post only links within anthropic.com.

Elsewhere on anthropic.com (4)

Something wrong here? Report a problem

A post on anthropic.com, published 9 September 2026, is cited by 17 distinct blogs to date (corpus.blog, measured 8 October 2026).