Constitutional AI and RLAIF
Bai et al. (arXiv:2212.08073, 2022) asked: what if we replaced the human labeler with an AI that reads a list of principles? Constitutional AI has two phases — self-critique and revision under a constitution, then RL from AI Feedback. The technique coined the term RLAIF and shipped in the Claude 1 post-training pipeline. On 21 January 2026 Anthropic published a rewritten Claude constitution: explanatory reasoning over prescriptive rules, a four-tier priority hierarchy, and the first major-lab formal acknowledgment of uncertainty about model moral status. Released under CC0 1.0.
This lesson isn’t interactive yet.
It is part of the curriculum and will get the same treatment as Phase 1 — a visual cover, hands-on labs, derivations with numeric checks and a quiz. Until then, the original lesson is the best place to read it:
Part of Phase 18 — Ethics, Safety & Alignment. Use the previous / next cards below to keep browsing the phase.