Iliad Intensive Curriculum
The Iliad Intensive is a month-long, full-time AI alignment course for students with strong mathematics, physics, or theoretical-CS backgrounds. These are the materials from the April 2026 cohort — mathematical exercises, self-contained lecture notes on topics from singular learning theory to debate, and pointers for further study. About 20 contributors developed them. We share them to invite feedback and enable independent study.
Foundations
- Prerequisites
A curated reading list of background worldview material and technical prerequisites (math, CS, deep learning) recommended before the Iliad Intensive.
A — Alignment
- AI Alignment Introduction
An opinionated tour of the AI alignment problem: alignment targets, problem decompositions (outer/inner alignment, training stories, inductive biases), goal-directedness and instrumental convergence, the risk landscape, and high-level solution approaches.
- Reward Learning Theory
The theoretical foundations of reward learning — how RLHF can (in principle) recover an aligned objective, when underspecification and misspecification break that story, and how assistance games reframe the problem.
- Alignment in practice
A tour of how frontier LLMs are actually aligned in practice — interventions at pre-training, post-training, and three stages of deployment — including methods, limitations, and the structure of safety cases.