The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
One run of an LLM on a task, saved as it happened: what it was given, what it did and what it replied. A lesson replays it, so every run prints the same thing and nothing is generated.
Weight on an input shows that the first layer reads it. It does not show that the reading reaches the move.
An LLM reads a network's weights · Six recorded sessions: an LLM is handed 1,315 weights as text and asked what the network was trained to do. Score each answer against the network, and study one it got wrong. 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.
Six recorded sessions: an LLM is handed 1,315 weights as text and asked what the network was trained to do. Score each answer against the network, and study one it got wrong.
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