AI for Beginners · 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 up to show where its knowing actually lives. It isn't in the pegs. Two new plain words fall out of it: weights and training.

CourseAI for Beginners
Lesson2 of 14
Builds onWhat it is
Where we left off

A plain board only echoes you

Remember the square board. Pour the coins into slot 2 and they pile under slot 2; into slot 5 and they pile under slot 5. Useful? Not very — it just hands back roughly where you poured.

For the board to do something worth having, pouring in at slot 2 should be able to come out somewhere you didn't pick by hand — somewhere the board has been made to send it. And the way to do that is to change not the pegs, but the floor they stand on.

The two pots

Manipulate the board

Picture two pots. A red one full of grease, a dark-blue one full of rubber paste. Dip a finger in each and wipe them across the floor of the board, until no bare wood is left.

Two cans: red grease and dark-blue rubber paste A red can labelled grease and a dark-blue can labelled rubber paste, side by side. Below them, a smear shows the two blending through every shade of violet. GREASE + RUBBER PASTE blend to every shade of violet
The two pots. Red grease makes a path slippery; blue rubber paste makes it sticky — and between them, every shade of violet.

Grease is slippery: where the floor is red, a coin slides through easily. Rubber is sticky: where it's blue, the coin resists and barely goes. Most of the floor is a blend of the two — every shade of violet in between. The pegs haven't moved an inch. But now a coin poured into slot 2 rides the warm, red trail across the floor and comes out under slot 5, because that's where the colour leads it.

Real grease and rubber wouldn't actually steer a coin sideways like this — that's not how the physics would work. It's a mental model, not a working machine. But it does exactly what a mental model needs to: colour on the floor decides which way a coin leans, and that's the part that matters.

A blank board and a trained board, side by side On the left, a board with a bare white floor: coins poured into slot two scatter into a mound under slot two. On the right, the same board with its floor smeared into a red-to-blue heat map: coins poured into slot two follow a warm red trail across the floor and gather under slot five. 12345 UNTRAINED · BLANK FLOOR poured at 2 → scatters under 2 TRAINING 12345 TRAINED · HEAT MAP poured at 2 → routed to 5
Same pegs, two different floors. A bare floor just scatters the coins under where you poured. A floor smeared into a red-to-blue heat map carries them wherever the warm trail leads — here, from slot 2 to slot 5.

That coloured floor is the whole trick. How red-or-blue each patch is — how strongly a coin is drawn through it or held back — is a weight. People also call it a parameter, especially when they're counting them up — a "three-billion-parameter model" simply means a floor with three billion of these patches painted on it. Same thing, two words. And the full map of colour across the floor is nothing less than what the board knows.

Here's where that count actually comes from. Picture our board as a simple grid: five pegs — five neurons — across, five rows deep. The painted floor lets a coin from any peg reach any peg in the row below, so every one of those pathways carries its own weight. Five pegs feeding five pegs is five times five: twenty-five separate pathways, twenty-five parameters, for just one hand-off between rows. Four hand-offs across five rows, and this one small board already holds four times twenty-five — a hundred parameters — before we've even stacked a second board on top.

Same pegs, different floor — a different board

Hand two people the identical wooden board and paint the floors differently, and they behave like two different machines. The pegs are shared and, on their own, know nothing. Everything a board has learned lives in the smear on the floor — never in the pegs.

The reveal

What has all this to do with AI?

Everything. The board you've been building — pegs, floor and all — is a working picture of an AI. You've already met its biggest idea; we simply hadn't said the word yet.

Lay the two side by side. The pegs are the AI's structure — fixed, the same for everyone who has that model. The smeared floor is everything this particular AI has learned: its own private map, and the whole reason it does what it does instead of something else.

The board's two halves, pulling apart An animated diagram. At rest, pegs sit directly on top of a red-and-blue painted floor, looking like one solid board. The two halves then drift apart: the pegs slide left onto their own plain card labelled structure, and the painted floor slides right onto its own card labelled trained floor, the weights. The cards separate fully, hold apart, then drift back together into one board, looping continuously. STRUCTURE — the pegs TRAINED FLOOR — the weights
The board's two halves, drifting apart and back together. On its own, the structure just floats — pegs with nothing to say. On its own, the floor is only colour — a map with nothing to hang it on. Only together do they make a working board.

This split is on purpose, and it isn't only a teaching trick. A real AI is packaged exactly this way: the structure and the trained weights are saved as two separate files, shipped together — one holds the shape, the other holds everything it learned, and neither is any use without the other.

And the act you pictured a moment ago — wiping grease and rubber across the floor until the coins flow where they should — is the heart of the matter. You smearing the board like that, patch by patch, until the right thing goes in and the right thing comes out: that is what training is. You trained the board. When the people who build an AI do exactly this — using mathematics instead of grease and rubber — "training" is the word they use for it.

Nobody does it by hand, patch by patch — there are far too many, and no one knows in advance what colour each should be. The floor is smeared in slowly, by the board being shown example after example: each time, the colour is nudged a touch — a little redder where a coin ought to have flowed, a little bluer where it shouldn't have. One example changes almost nothing. But over millions of them, a blank floor becomes the rich map you saw above — one that reliably carries the right thing in to the right place out. It's done once, by the people who build the AI, at enormous effort, long before it ever reaches you.

Finished, and frozen

When it reaches you, the paint is dry

This is the part that settles most people's worry.

Training is the floor being painted. Using the board — the makers call it inference — is something else entirely: you drop a coin through a floor that is already finished and dry. The colour doesn't change because you used it. The board can't learn about you while you talk to it, can't quietly rearrange itself, and is the exact same board for you as for everyone else. What you send through is read to produce a result — and then the board is precisely as it was.

Painted once, by the makers Dry when it reaches you The same board for everyone Using it teaches it nothing
Deeper

Stack the boards, and you get depth

One board can only do so much. So we stack them: the coins that fall out of the bottom of the first board are poured straight into the top of the next.

Each board has its own painted floor — its own map. A coin threads down through all of them in turn, nudged by one map after another, before a result finally drops out the bottom. That stacking is all the word deep means in "deep learning": many boards, one on top of the next.

Three coin boards stacked into layers Three boards stacked one above the next, each with its own differently painted red-and-blue floor. A single coin threads down through all three in turn, swinging left through the first board, right through the second, and back toward the centre through the third, before a result drops out of the bottom. The stack is labelled layers, or deep. COINS IN BOARD 1 BOARD 2 BOARD 3 A RESULT DROPS OUT LAYERS ( DEEP )
Three boards stacked, each with its own differently trained floor. What drops out of one is poured into the next, so the coin is pulled left, then right, then back toward the centre — shaped by one map after another. Stacking boards is all "deep" means.

One note on size, so the drawing doesn't mislead you. These boards are 5 slots across and stacked three high, so you can see them. A real one has floors carrying billions of coloured patches, across far more boards than three. Not a different idea — the same idea, at a size no drawing can hold.

Next

From coins to words

We've talked in coins and slots. But an AI takes in words, not coins. The next lesson shows the one simple move that turns this board into something that can read and write — and why it answers one word at a time.

The whole picture, continued

The glossary, 9 rows longer

Everything from the lessons before this one, plus what this lesson added.

The board The word for it
The board and its pegsThe structure — the model
A single pegA neuron
A single step from one peg to the nextA connection
How red or blue a patch of floor isA weight — a parameter
The whole painted floorThe trained model
Boards stacked, one on the nextLayers — "deep"
Smearing the floor in, coin by coinTraining
Dropping one coin through a finished boardUsing it — inference
Which slot you pour intoYour input — your prompt

9 rows now. It keeps growing as the course goes on.

Lesson 2 of 14

Sign in to orqo

Choose how you'd like to continue.

More ways to sign in are on the way.