Interpretability & Alignment

Looking inside models — features, circuits, superposition — and the techniques and evaluations used to make capable systems behave as intended.

3 lessons • 27 min read

1. 01

   Mechanistic interpretability: features, circuits and superposition

   Mechanistic interpretability tries to explain a trained network the way one would reverse-engineer a compiled program: identify the variables it represents and the operations that combine them. This lesson covers the core vocabulary, the tools built on it, and the state of the debate about how far those tools reach, as of November 2026.

   10 min read
2. 02

   Alignment techniques: preference learning, constitutions and oversight

   A pretrained language model imitates its training text; nothing in next-token prediction says "be honest", "refuse to help build a weapon" or "admit uncertainty". Alignment techniques add those targets after pretraining. This lesson works through the main families — learning from human preferences, learning from written principles, and oversight schemes for tasks humans cannot easily judge — and where each is known to strain, as of November 2026.

   8 min read
3. 03

   Evaluating safety: dangerous capabilities, deception and control

   Before a frontier model is released, developers and outside evaluators try to answer two questions: what harmful things could it do, and would it choose to do them — including hiding that choice from the people testing it. This lesson covers how those questions are tested, what constructed "model organisms" of deception show, why test-aware models complicate evaluation, and the AI control approach, as of November 2026.

   9 min read