Phase 2: Control & Containment · ~60 minutes · Python (stdlib · four-tier priority resolver)

Constitutional AI and Rule Overrides

Anthropic's January 22, 2026 Claude Constitution runs 79 pages and is CC0.

Hiring signal: Can operate constitutional ai and rule overrides in production

Introduction

It moves from rule-based to reason-based alignment and establishes a four-tier priority hierarchy: (1) safety and supporting human oversight, (2) ethics, (3) Anthropic guidelines, (4) helpfulness. Behaviours split into hardcoded prohibitions (bioweapons uplift, CSAM) that operators and users cannot override and soft-coded defaults that operators can adjust within defined bounds. The 2022 original (Bai et al.) trained harmlessness via self-critique and RLAIF against a constitution. The honest caveat: reason-based alignment relies on the model generalising principles to unanticipated situations. Anthropic's own 2023 participatory experiment showed ~50% divergence between public-sourced and corporate principles; the 2026 version did not incorporate those findings.

Type: Learn Languages: Python (stdlib, four-tier priority resolver) Prerequisites: Phase 15 · 06 (Automated alignment research), Phase 15 · 10 (Permission modes) Time: ~60 minutes

Objective

Learning objectives

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.

Key terms in this lesson

Constitutional AI