Blog topic
Inside the model: interpretability and alignment
What a trained network has learned and how one finds out: probes, the Othello experiment, features and circuits, and the research on aligning models.
Articles

3 Nov 2026
Does a language model know what it is talking about?
Train a small transformer on nothing but lists of moves from the board game Othello, with no picture of the board, and ask whether it holds the board in its head. A probe says yes; editing the board inside the network and watching the move change says it uses it.

22 Oct 2026
How a language model is turned into an assistant
A model that has read the internet continues text; it does not answer questions. Three stages turn it into an assistant: demonstrations, comparisons, and a reward with a leash. The InstructGPT numbers of 2022, and the Bradley-Terry probability worked for two answers.
In the masterclass
Units on this topic