The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
A statement of what a program or a network must do, exact enough to test against. For a small network it can be a rule that names the right output for every possible input.
The first layer the editor wrote in session 1: six rows of four weights. The other 26 rows are zero and aren't shown. Move the column box to 2 to pick out ball_dx.
An LLM writes a network's weights · Five recorded sessions: an LLM writes every weight of a paddle network from the game's source and one sentence. Score each against its specification, test its design claims, and edit one by hand. 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.
Five recorded sessions: an LLM writes every weight of a paddle network from the game's source and one sentence. Score each against its specification, test its design claims, and edit one 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