AI for Beginners · 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 it into something that reads and writes — and shows that "talking" is nothing grander than guessing the next word, again and again.

CourseAI for Beginners
Lesson3 of 14
Builds onWhat's inside
Where we left off

So far, it moves slots — not words

A trained board is a mapping machine. Pour something in at the top, and the heat map on the floor carries it to an output at the bottom. Simple enough — but everything we've poured in and read out has been a bare slot, a position with a number.

To read and write, the board needs to deal in words. And the leap to get there is far smaller than you'd think — in fact, we don't have to change the board at all.

The leap

Let a slot be a word

Take the very same board and relabel the bins along the bottom. Instead of 1, 2, 3, 4, 5, write words. Nothing inside changes — only the labels.

Now pouring the coins in stops meaning "drop at slot 2" and starts meaning "here are the words so far." And the bin the coins pile up in stops being a number and becomes the board's answer to a single question: what word comes next? This is still the trained, painted floor from the last lesson — so the pile won't just fall straight down from where you poured. Feed it "Cat eats ___", and the warm path carries the coins sideways, stacking highest under mouse.

A trained coin board whose bins are words The words "Cat eats" are fed into the top of the board, whose floor still carries the red and blue heat map from the previous lesson. A warm diagonal channel carries the coins away from straight down and toward the bin labelled mouse, which is not directly beneath the funnel. The bins along the bottom are labelled shoe, grass, fish, mouse and bird. The coins pile highest under mouse, with a few under fish and bird, and almost none under shoe or grass. THE WORDS SO FAR Cat eats ___ THE TRAINED FLOOR shoe grass fish mouse bird THE MOST LIKELY NEXT WORD
The same board, its floor still carrying the red-and-blue heat map from Lesson 2. Feed in "Cat eats ___" and the warm path carries the coins sideways, piling highest under mouse — not the bin straight below the funnel. A clear favourite, with a few runners-up.

That's the whole leap. The machine that sorted coins into numbered bins now takes words in and gives a word back — because we agreed to read its slots as words. Notice, too, that mouse isn't the bin directly under the funnel: it's wherever the trained floor leads. An untrained board would just pile up straight down the middle, same as Lesson 1. This one has learned to send "Cat eats" specifically toward mouse.

One small guess

It only ever guesses the next word

Notice what the board did — and what it didn't. It didn't compose a sentence or plan an answer. It answered one tiny question: given the words so far, which word most likely comes next?

You do this yourself without noticing. Read "Once upon a ___" and your mind hands you time before you've even finished. The board does exactly that — and it's the very same prediction from Lesson 1, a pile that's tall in the likely place, only now the bins are words. Mouse is tallest; fish and bird get a few coins; grass and shoe almost none. A favourite, and some runners-up.

Again, and again

One word at a time

But a single word isn't a conversation. So here is the trick that turns one small guess into whole paragraphs: it simply does it again.

Guess a word. Write it on the end. Now feed the whole, slightly longer line back into the board and guess the next word. Then again, and again. "Cat" leads to "eats"; "Cat eats" leads to "mouse" — and a sentence builds itself, one word at a time.

The next-word loop Three passes through the board. First, "Cat" goes in and "eats" comes out. Then "Cat eats" goes in and "mouse" comes out. Then "Cat eats mouse" goes in and the sentence ends. A looping arrow shows the output being added on and the board run again. YOU GIVE IT A START THE NEXT WORD Cat eats Cat eats mouse Cat eats mouse · end · ADD IT ON, RUN AGAIN the board is the same every pass — only the line grows
The loop. Each pass, the board guesses one more word and it's added to the end; then the whole line goes back in. "Cat" → "eats" → "mouse" — a sentence, built one word at a time.

That loop is the entire engine. Every answer you have ever seen an AI give — however long, however fluent — was laid down this way: one most-likely word, then the next, then the next.

What this explains

Completion, not composition

Once you can see the loop, a lot of what the thing does stops being mysterious.

It writes left to right and seems to type before your eyes — because it is, quite literally, producing one word at a time. It doesn't think up a finished answer and then read it out to you; it is always just extending what's there by one likely word. It isn't a mind composing a reply. It's the most well-read machine ever built, finishing your sentence — and then finishing that, and then finishing that.

The short version

Talking is next-word prediction in a loop. The board guesses the likeliest next word, tacks it on, and runs again. Nothing more mystical is going on.

Next

One word wasn't quite the right word

There's one simplification we've been quietly making. We called the bins "words" — mouse, fish, bird — because it was easier to picture. That's not quite precise.

Real systems don't cut language into whole words. They cut it into smaller pieces — sometimes a whole word, sometimes only part of one. The next lesson names that piece properly, and gives us the word missing from our table so far.

The whole picture, continued

The glossary, 3 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
+ New in this lesson
The bins, relabelled with tokensThe vocabulary — every token it could pick
The tallest pile among the binsThe prediction — the likeliest next token
Feeding the growing line back in and running againThe loop — how one guess becomes a sentence

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

Lesson 3 of 14

Sign in to orqo

Choose how you'd like to continue.

More ways to sign in are on the way.