Constitutional AI

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

synthetic-sciences Updated 4.4k repo stars
An OpenScience session comparing EGFR inhibitor potency: the trace shows the search, the written files, the analysis run and the answer with a results table

File contents

synthetic-sciences/openscience commit 63eebdb18c

Frequently asked questions

npx get-skill add synthetic-sciences/constitutional-ai