The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
Reading a network's weights, working out what they compute, and writing new values directly, with no training loop. The name comes from a 2026 post in which a language model does the reading and writing.
The policy's weight matrix as a picture: blue is positive, red is negative. Move over a cell, or use the Row and Column boxes, to read each weight. The "left" and "right" rows are mirror images, and the "stay" row is blank.
Weight-space programming: what it is, and what has been shown · A language model reads and writes another network's weights with no training loop: the published experiments, their limits and the criticism, and one edit you make by hand. About 30 minutes.
1286 terms in the glossary, each with the lesson that teaches it.
Every word you'll meet in AI and machine learning, explained in everyday language.
A language model reads and writes another network's weights with no training loop: the published experiments, their limits and the criticism, and one edit you make by hand.
Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write