AI for Beginners · 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 the last of the worry, the whole reason this course exists, can finally go.

CourseAI for Beginners
Lesson14 of 14
Builds onAlignment
The one thing that can't happen

The model you talk to cannot change

This is worth being completely unambiguous about, because it's the single biggest fear this course set out to remove. Go back to Lesson 2: using it teaches it nothing.

The floor is painted once, by the makers, long before it ever reaches you. Talking to it is inference, not training — a coin dropping through a floor that is already finished and dry. It cannot quietly learn your secrets. It cannot rearrange itself around your conversation. The model answering you right now is structurally, mechanically incapable of changing because you used it. That part isn't a policy or a promise. It's just how the model works.

A separate question

What happens to the transcript is a different matter

Here's the nuance. The model itself can't learn from you live — but the company running the servers behind whichever door you used can still keep a copy of what you typed, the way any website can log a form submission.

Whether they do, and what they do with it afterward, is a disclosed business choice, not a fact about the model. A copy might be kept briefly for abuse monitoring. It might, per the product's own stated policy, be used later — in bulk, well after the fact — to help shape a future, different model. Or it might never be kept at all. This is exactly why Lesson 9's "which door" question matters here too, not just for price.

The free public chat

Check the settings

  • Text goes to the company's own servers.
  • Many free consumer tools default to allowing conversations to inform future training.
  • Usually adjustable — look for a data or privacy setting, and an opt-out.
A business or API product

Built for the sensitive work

  • Text is processed for that one reply, through infrastructure the business chose.
  • Commonly built on a stated Zero Data Retention guarantee — nothing kept, not even briefly.
  • The exact standard for work like due diligence, legal, or health.
The term for the strong guarantee

Zero Data Retention

You'll see this phrase, or its short form ZDR, on pricing and policy pages. It's a specific, contractual promise: the provider keeps no copy of what passed through after the reply is sent — not for training, not for review, not at all.

It's a stronger guarantee than "we won't sell your data" — it means there is nothing left to sell, review, or leak, because nothing was retained in the first place. This is the standard orqo itself is built on: split-plane by design, so the control plane holds none of your content at rest. The full, detailed version of exactly how is laid out on our security page, if you want it.

A few simple habits

Nothing here needs to be memorised

One instinct covers almost every case: treat a free public chat tool like a postcard, not a locked drawer, unless you've confirmed otherwise.

Check the privacy setting before you paste something sensitive Business tools built for sensitive work usually say "zero retention" for a reason The model can't learn your secrets — the company behind it might still log them When unsure, ask which door, and what its policy actually says
The end of the numbered path

You now have the whole model

Fourteen lessons ago this started with a wooden machine — coins, pegs, a shape that appears on its own. Everything since has been the same model, opened up a little further each time.

That was always the point, more than any single fact in the table above. Not to make you an engineer — to make the mystery smaller than the fascination. A model is a structure. Weights are what it learned. Tokens are its alphabet. Scale is just more of the same idea. A mistake is a stray pick, extended with nothing to check it. A prompt is where you pour. An API is a door. And what you type is safer than the fear made it feel, once you know exactly what "safe" is actually promising.

This course is built to keep growing — new lessons, deeper detours, whenever there's more worth explaining this same way. For now, this is everything, start to finish. Thank you for reading it.

The wooden machine from the first paragraph above is real, and it has its own history worth reading — Francis Galton, 1874, a glass box of falling shot. Visit the Galton board page.

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
Background, examples, or a role, added right into the pourContext
Asking for many small steps instead of one big leapChain-of-thought prompting
A friendly chat window built around the boardA product — like ChatGPT or Claude.ai
A door that lets software pour in and read out directlyAn API
What each million tokens costs to send in or get backAPI pricing — pricier for bigger models, and for output
Recalling the start of the line instead of re-pouring itCached tokens — priced far cheaper than fresh input
The board asking the app to go do something real before it answersTool use — or function calling
One shared shape for listing tools and calling themMCP — Model Context Protocol
A program that speaks that shape and hands back its whole toolboxAn MCP server
The loop deciding, acting, and watching what happened, on repeatAn agent — a model with tools, looping until the goal is met
Deciding its own steps, and knowing when it's doneAutonomy
Reading what just happened before deciding what's nextReactivity
Starting on its own, from a schedule or an eventPro-activeness
Talking to other agents, and to people, not just toolsSocial ability
Search first, hand the model what you found, then let it answerRAG — Retrieval-Augmented Generation
Folding the search step into the loop, so it can search again if neededAgentic RAG
The first, giant reading pass, before the floor is fine-tuned at allPretraining
A second, much smaller painting pass, aimed at a narrower targetPost-training — or fine-tuning
A person ranking draft answers, best to worstRLHF — Reinforcement Learning from Human Feedback
A small helper trained to predict which answer people preferA reward model
Making a model's behavior actually match what people wantAlignment
+ New in this lesson
A promise that nothing sent through is kept, even brieflyZero Data Retention — ZDR
Whether a transcript might later help train a future versionA data-usage policy — check the settings

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

Lesson 14 of 14

Sign in to orqo

Choose how you'd like to continue.

More ways to sign in are on the way.