Skip to content
Science, DecodedContext Jamming

Paper Reading Lab

Constitutional AI: Harmlessness from AI Feedback

Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, and 46 others (Anthropic) · 2022

arXiv preprint (Anthropic)Open paper ↗PDF ↗

Why this paper

Its "equation" is a procedure. Reading it carefully shows exactly why the tempting AdS/CFT analogy in Module 7 cannot be a mathematical duality.

Pass 1 of 8

Research question

What is the research question?

Where to look: Abstract and Introduction ("Motivations")

Your read

Background: Module 7, The Physics–Biology–AI Connection Lab →