My First Language Model
This is the original LLMs Unplugged workshop, and still the best place to start. Participants count word patterns in a real text, record them as tally marks on Grid A sheet of grid paper with the vocabulary written down the side and across the top. Training fills each cell with tally marks for how often the row's word was followed by the column's word; generation reads a row and rolls against it. It's the original LLMs Unplugged apparatus. View in glossary , then roll a d10 to generate brand-new text from those patterns. Somewhere between the tallying and the dramatic readings, the penny drops: this is what Chatbot (ChatGPT, Claude, Gemini) A product that wraps an LLM in a conversation. ChatGPT is OpenAI's, Claude is Anthropic's, Gemini is Google's, and there are many others. On this site we often name ChatGPT or Claude as shorthand for any of them: the concepts apply equally to every modern LLM chatbot, whichever one you use. View in glossary does, just vastly scaled up.
We’ve delivered it to school students, undergraduates, teachers, and senior executives in industry and government. It needs no coding and no maths beyond counting and percentages.
Choose your length
One lesson, three lengths. Each length keeps everything from the one before it and adds a module:
| Length | Modules | Adds |
|---|---|---|
| 60 minutes | Training + Generation | the core train-then-generate loop |
| 90 minutes | + Pre-trained Model Generation | what happens with a bigger model and more data |
| 2 hours | + Agentic AI | how models use tools to act on the world |
Every length opens with a quick icebreaker and scene-setting (who’s used ChatGPT? how do you think it works?) and closes with a “scaling up” discussion connecting the paper model to modern LLM (Large Language Model) A language model trained on a very large amount of text, with billions of parameters. The hand-built models in these lessons are tiny language models; ChatGPT, Claude and Gemini are large ones. The core principles are identical. The difference is scale. View in glossary , then Q&A.
Suggested timing (90-minute version)
- 0:00 kick-off — icebreaker, then: today we build our own AI, small and simple, but using the exact same approach as the big ones
- 0:20 Training — tally word patterns from a text into the grid
- 0:40 Generation — roll dice to generate new text from the grid; share back with dramatic readings
- 1:00 Pre-trained Model Generation — same dice game, but with a printed booklet trained on a whole book
- 1:20 close — scaling up: how does this connect to ChatGPT? how has this changed how you’ll use these tools?
For the 60-minute version, drop the pre-trained booklet section and tighten the close. For the 2-hour version, add Agentic AI after the pre-trained section (about 20 minutes) and give every discussion a little more room to breathe.
You will need
For each pair (or small group) of participants:
- pen or pencil
- a printed grid template (or any grid paper)
- a d10 die (any die works with a little improvisation)
- some training text: a few pages of a kids’ book is ideal, but anything works
- 90 minutes and up: a pre-trained model Booklet A printed dice lookup table for a text: one entry per previous word (or pair of words, in a trigram booklet), listing the possible next words with the d10 range that selects each. A booklet is a pre-trained model you can generate from without having trained it. View in glossary —the Materials page has ready-to-print booklets for several texts, or you can generate your own
Plus a projector for the slides.
Before you deliver
- print the grid templates, and the booklets if you’re running 90 minutes or longer (one per pair; a mix of different texts makes the share-backs more fun)
- if your group isn’t yet comfortable with dice-based weighted sampling, run the Weighted Randomness module first as a warm-up (add about 30 minutes)
- got extra time, or a group that wants more? the Sampling module makes a great add-on after generation—it shows how Temperature A dial on how much the model respects its own counts. Low temperature sticks to the favourites; high temperature flattens the odds until every option is roughly equal. A real model divides its scores by the temperature before turning them into probabilities. With raw counts that trick does nothing, so the hand-run version adds a constant to every count instead. View in glossary changes the character of the output without changing the model
Using the slides
- My First Language Model (60 min) (presenter guide PDF)
- My First Language Model (90 min) (presenter guide PDF)
- My First Language Model (2 hours) (presenter guide PDF)
The presenter guides are PDFs with every slide followed by a page of its speaker notes—handy if you'd rather prepare away from the browser.
The slides run in your browser, and every slide carries full presenter notes—what to say, what to watch for, and how long each part should take. A few keys worth knowing:
- f toggles fullscreen—do this before you start presenting
- s opens the speaker view in a separate window, with the presenter notes, a timer, and a preview of the next slide (drag it to your laptop screen and put the slides on the projector)
- o shows an overview of all slides, handy for skipping ahead if you're running short on time