Skip to content

AI Folks Labs

See it work.

Interactive explainers that take one hard idea in AI and make it something you can touch.

Scroll

Why these exist

Learn AI visually.

Every lab takes a concept that is usually explained with a metaphor and replaces the metaphor with the thing itself. You type, drag, break it, and watch what happens.

Try clicking on one of the labs below.

Live

How a language model actually works

Type a sentence and watch it become tokens, embeddings, attention and a prediction. The four stages, playable.

10 minBeginner
Live

Gradient descent you can feel

Drag a ball down a loss surface. Change the learning rate and watch it overshoot, stall, or find the valley.

6 minBeginner
Live

The tokenizer playground

Why “strawberry” has three r’s but the model cannot count them. Paste anything and see the pieces.

4 minBeginner
Coming Soon

Why models hallucinate

Break a retrieval pipeline on purpose. Watch a confident, well-formed, entirely invented citation appear.

8 minIntermediate
Coming Soon

Diffusion: noise to image

Scrub the denoising steps back and forth and see structure emerge out of static.

7 minBeginner
Coming Soon

The map of meaning

Fly through an embedding space. Find what sits near “bank”, and why that is a problem.

6 minBeginner

After the labs

Playing with it is an hour.
Building it is six months.

Every lab is a five-minute version of something you construct properly in the programme, tokenisers, attention, retrieval, evaluation, deployment.