AI for Beginners · 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 — matters enormously. This lesson turns that into technique. None of it is a trick. It's all just tilting the board on purpose.

CourseAI for Beginners
Lesson8 of 14
Builds onWhy it's sometimes wrong
The oldest lever

You've had your hand on this since Lesson 1

Go all the way back to the square board. Five slots, one floor — and it was you who chose where to pour. Pour at slot 2, the pile formed under 2. Pour at slot 5, it formed under 5. The model never picked that; you did.

A prompt is just a much richer version of the same choice. Every word you type before you hit send is part of where you're pouring — and the whole floor responds to it before the model ever starts leaning toward an answer.

Specific pour, confident pile

Vague in, scattered out

Here's the practical version of what Lesson 7 warned about. A vague prompt leaves the floor's warm patches spread thin across many roughly-equal bins — exactly the near-tie condition where a stray pick is likeliest. A specific prompt concentrates the warmth into one clear channel.

A vague prompt versus a specific prompt Two boards side by side. On the left, "Tell me about dogs" produces a scattered pile of nearly equal height across five bins. On the right, "In two sentences, why do Labradors make good family pets" produces one clearly tall pile concentrated in a single bin. "Tell me about dogs" breedshistorycaresizetraining NO CLEAR FAVOURITE "In two sentences, why do Labradors make good family pets" breedshistorytemperamentsizetraining ONE CLEAR CHANNEL
Same board, same floor — only the prompt changed. Vague input leaves the pile spread thin across near-ties. Specific input — a length, an angle, a real question — pulls it into one confident channel.

Neither model is broken. The specific one just gave the floor far less room to be uncertain in.

Give it more floor to stand on

Context

Training paints the floor once, for everyone. But you can hand the model context — background, examples, a role to take on — right there in your prompt, and it warms the relevant patches just for that one pour.

Paste in the document you're actually asking about. Show it one example of the style you want. Tell it to answer as a specific kind of expert. None of that retrains anything — Lesson 2's frozen floor is still frozen — but it gives this one pass a much narrower, better-informed channel to fall into, the same way a detailed question did in the figure above.

Let it take smaller steps

One big leap, or many small confident ones

Remember the loop from Lesson 3: every pass is one small, confident pick, fed back in for the next. A long, careful answer isn't one giant leap of insight — it's many small ones, each fairly safe on its own.

Asking it to "think step by step," or to lay out its reasoning before giving a final answer, is a real technique with a name: chain-of-thought prompting. It works because it forces more, smaller loop passes instead of one big one — and a small confident step is far less likely to be a stray pick than a single leap straight to the answer.

It doesn't hold a grudge

Every pour is a fresh one

If the first pile isn't the one you wanted, you're not fighting the model — you're just choosing a better slot. Rephrase, add the detail you left out, try a different angle.

This is the same reassurance from Lesson 1, put to use: it doesn't change as you use it, and it isn't quietly getting annoyed at your third attempt. Each pour is independent. A better prompt this time doesn't need to undo anything from last time — there's nothing to undo.

What a chat window is actually doing

Conversations

The model itself keeps nothing between messages. No memory, no notes, nothing warm left over from your last question. Every pour is a fresh one — Lesson 3's loop starts over from nothing, every single time.

So how does a back-and-forth conversation work at all? Your chat interface is doing the remembering for it. Every time you hit send, it quietly gathers up the whole exchange so far — everything you've said, everything it's said back — and pours that entire transcript in again as fresh context for this one message. That's the same "context" from a moment ago, just handed over automatically instead of typed by hand. Take the transcript away, and the model wouldn't know a conversation had ever happened.

That's also the ceiling on how personal this can feel: the memory only exists inside that one growing transcript, gone the moment it ends. Curious how a platform gives an assistant memory that actually persists across conversations?

The backpack: what gets sent grows every message — and starts costing real money Four panels side by side, one per message you send, with the model fixed at the top of each and your most recent message always at the bottom, like a chat window. Model responses are drawn taller than your messages, since replies are usually the longer half. The first panel sends just your first message. The second and third panels box a growing amount of carried history beneath the model, with each new message outlined as new below the box. The fourth panel jumps ahead to message twelve: the box has grown into a dense, zebra-striped mass representing many earlier messages and responses, marked with an ellipsis for everything compressed out of view, with only the two most recent turns still shown in full. The arrow into the model gets shorter as the box grows, until by message twelve it is barely more than a hop — showing how close a long conversation sits to its limit, and how much more expensive each message has become. MESSAGE 1 MESSAGE 2 MESSAGE 3 MESSAGE 12 …many messages later… Message 1 1 message sent — a fraction of a cent Message 1 Response 1 Message 2 3 pieces sent — still pennies Message 1 Response 1 Message 2 Response 2 Message 3 5 pieces sent — pennies, but climbing Message Response Message 12 23 pieces sent — real money now
The backpack. The model sits at the top; your most recent message always sits at the bottom, like a chat window. Responses are drawn taller than messages, because replies are usually the longer half. By message twelve, the boxed history has grown into a dense zebra-striped mass — sent again, in full, every single time. A short conversation costs pennies; a long one starts costing real money, because every message pays to resend everything that came before it.

That growing cost is exactly the kind of problem worth solving at the platform level, not one prompt at a time. See how orqo manages it.

What good prompting can't fix

You're tilting a board, not changing what it is

There's a real ceiling here. No phrasing, however careful, changes what the model fundamentally does.

The best prompt in the world still can't make it count letters it never saw one at a time, or know something after its training ended, or turn a genuinely thin, thinly-covered topic into a well-painted one. Good prompting narrows the lean within what the model actually knows. It doesn't hand it knowledge it never had.

Next

The chat box isn't the only door

Everything so far has happened inside a chat window — ChatGPT, Claude, or something built to look like them. That window is a product, not the model itself.

The next lesson shows the other door: the same model, reachable directly, priced by the token — and how a business builds its own product on the exact same intelligence.

The whole picture, continued

The glossary, 2 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
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
One bin's label, preciselyA token — not always a whole word
How many bins there are, in totalVocabulary size — tens of thousands
The size of the mountain of text it was shownTraining data — measured in tokens
A bin's own address, plotted in spaceAn embedding — meaning turned into a list of numbers
How close two addresses sitSimilarity — how related two things are
The measurement's real name, out in the wildCosine similarity — same idea as similarity, different name
About meaning, not exact spellingSemantic
A neighbourhood of addresses that share a topicA domain — a cluster of related meaning
Scanning every address for whichever one sits closest to a new pointNearest neighbor — the closest real match to a computed point
A small, separate machine that only plots words as points — it never writes a sentenceAn embedding model — not the same as a language model
The total number of coloured patches, across every boardParameters — the number people quote
How many tokens the funnel can hold in one pourInput tokens — the context window
How many tokens come back outOutput tokens — what it writes back
Everything you've met so far, built at real-world sizeA Large Language Model — an LLM
A shorter pile winning, extended forward with full confidenceA hallucination
The point where the training reading stoppedThe knowledge cutoff
How sharp or blended the colour stays before a coin is pouredTemperature — the dial on how often a stray pick wins
Pouring the same slot twice, not always the same pileNon-deterministic — same input, no guaranteed identical output
+ New in this lesson
Background, examples, or a role, added right into the pourContext
Asking for many small steps instead of one big leapChain-of-thought prompting

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

Lesson 8 of 14

Sign in to orqo

Choose how you'd like to continue.

More ways to sign in are on the way.