The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
Changing a specific thing a model knows by rewriting a small part of its weights, without retraining. Judged by reliability, generalization, locality and what else it damages.
Then divide every cell by k · k = 5. That is the added matrix of the edit below.
Editing one fact · A rank-one change to one matrix rewrites what a product is made from; then reliability, generalization, locality, and what breaks after many edits. About 40 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 rank-one change to one matrix rewrites what a product is made from; then reliability, generalization, locality, and what breaks after many edits.
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