AI Glossary

By Lee Robinson

I keep meeting the same words: pretraining, attention, KV cache, reward hacking. This is my running list of them, each explained the way I wish someone had explained it to me first. One idea per page, in plain English, with the technical term right after.

The order builds on itself. Foundations come first, then how text turns into numbers, then training, behavior, and serving. You can read it start to finish like a short book, or land on a single page and get what you need. It started as the notes behind my longer post, Understanding AI.

New here? Start with Machine Learning and follow the arrows.

Foundations

The mental model: what a model is and how it learns at all.

Tokens & Embeddings

How text becomes the numbers a model can work with.

Transformers

The architecture behind every modern language model.

Training

How a model learns from data, one tiny adjustment at a time.

Fine-Tuning & RL

Turning a raw base model into a useful, aligned assistant.

Model Behavior

How tone, persistence, and personality get trained into a model.

Inference

Running a trained model in production, and why it gets fast.

Using Models

The knobs and ideas you meet when you actually build on models.

Evals & Measurement

Turning fuzzy progress into numbers you can trust, and reading the charts honestly.