A short course

AI for Beginners

No math. No jargon. One mental model — a board — that holds together from the first lesson to the last.

Lessons14, short
ForCurious beginners
NeedsNo technical background
How this works

One board, start to finish

Most explanations of AI reach for a new picture on every page, and the pictures don't fit together. This course uses a single mental model — a coin board — and builds everything on it.

Each lesson stands on the one before it. By the end you won't have the mathematics, and you won't need it. You'll have something more useful: a picture that's roughly right, that you can actually hold in your head, and that quietly answers the questions that tend to worry people most.

The lessons

What we'll cover

From "what is this thing" to "is it safe to use." Start at the top; each one takes a few minutes.

Lesson 1 — What it is

You don't need any mathematics, and you don't need to be "good with computers." Using a single, simple machine — one you could ...

Read lesson
Lesson 2 — What's inside

In Lesson 1 the board was a model — and a plain one only ever echoed where you poured the coins in. This lesson opens the board...

Read lesson
Lesson 3 — Why it can talk

In the last two lessons the board took something in and sent it somewhere out. This lesson makes the one small leap that turns ...

Read lesson
Lesson 4 — Tokens

In the last lesson we let a slot be a word, to keep things simple. That was a small lie, told on purpose. This lesson gives you...

Read lesson
Lesson 5 — Embeddings

A token doesn't touch the floor as a word — it has to become a list of numbers first. This lesson shows what that means, why "c...

Read lesson
Lesson 6 — Scale

Back in Lesson 2 we admitted something: our boards were five slots wide and three deep so you could actually see them, but a re...

Read lesson
Lesson 7 — Why it's sometimes wrong

Billions of parameters. Trillions of tokens of training. Underneath all of it, this is still a model making a prediction — and ...

Read lesson
Lesson 8 — How to talk to it

Lesson 7 ended on a promise: if a stray pick can tip a whole sentence, then what you type — before any of that happens — matter...

Read lesson
Lesson 9 — One model, many doors

For most people, "AI" means a chat window — ChatGPT, Claude. That window is a product, not the model itself. This lesson shows ...

Read lesson
Lesson 10 — MCP

Lesson 9 showed a model asking for one tool. Real use needs dozens, from services that have never heard of each other. This les...

Read lesson
Lesson 11 — Agents

One tool call was Lesson 9. This lesson asks what happens when one isn't enough — when a model has to decide, act, observe, and...

Read lesson
Lesson 12 — RAG

Training is frozen, and it never saw your own documents in the first place. This lesson names the standard fix — three ideas yo...

Read lesson
Lesson 13 — Alignment

Next-token prediction alone doesn't explain why a model answers you helpfully instead of just continuing your sentence, or why ...

Read lesson
Lesson 14 — Is it safe?

One door or the other, you've been sending your words somewhere. This last lesson answers what actually happens to them — so th...

Read lesson

Begin with Lesson 1

It's the foundation the rest stand on, and it's the one that does the most to take the mystery out of the whole subject.

What is this thing, really? →
Beyond the fourteen lessons

Pro — runnable code, not outlines

Once the model makes sense, the next step is running a real, tiny one yourself. This tier is for that: actual code, copy-paste-able, small enough to read top to bottom.

Genuinely past beginner material

Going deeper — the mechanisms themselves

The fourteen lessons describe what the model does. This tier is for anyone who's finished them and wants to see how — real architecture, still built on the same coin-and-pegs vocabulary.

Sign in to orqo

Choose how you'd like to continue.

More ways to sign in are on the way.