Events, programs, and opportunities from MAIA. Join mailing list

Alignment via Written Principles

Fall 2026Week 3

← All weeks

This week, we discuss how AI models are aligned via written principles and guidelines, also known as model constitutions or model specs. We begin by studying the technical underpinnings of constitutional AI and deliberative alignment, two approaches pioneered by Anthropic and OpenAI respectively. We discuss how these approaches shape model behavior and also discuss the extent to which they’re effective. We later read excerpts from Anthropic’s Claude Constitution and OpenAI’s Model Spec and analyze their different approaches, including their philosophical implications on AI. We conclude with research that explores how effective deliberative alignment is in preventing scheming. The goal of this week is to understand what model constitutions/specs are, learn how they are trained into models, and form opinions on how they should be constructed.

Week 3 readings

Constitutional AI: Harmlessness from AI Feedback

Yuntao Bai et. al, Anthropic

December 15, 2022

Claude’s New Constitution

Anthropic

January 22, 2026

OpenAI Model Spec

OpenAI

August 18, 2026

Stress Testing Deliberative Alignment for Anti-Scheming Training

Bronson Schoen et. al, Apollo Research and OpenAI

September 17, 2025

Additional readings