{"data":{"slug":"constitutional-ai","etype":"paper","name":"Constitutional AI (2022)","cat":"Alignment","subtitle":"Anthropic's method: models critique themselves against written principles.","summary":"Instead of scaling human labeling of harms, Constitutional AI has the model critique and revise its own outputs against an explicit constitution, then trains on the result (RLAIF). It powers Claude's character, made the principles inspectable, and pointed toward oversight that scales beyond human review.","attrs":null,"kf":null,"aliases":["CAI","RLAIF"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://arxiv.org/abs/2212.08073","label":"arXiv 2212.08073"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T08:41:50+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}