Official curated learning paths
The rooms that go with the maths labs, from arrows on a grid to how a language model picks its next word. Play a warm-up before its lab, and the rest alongside it.
Froga
What Words as arrows builds on: why a computer needs words as numbers, when two arrows point the same way, subtracting one arrow from another, and analogies in plain words. About ten minutes.
Froga
What Chance machines builds on: a chance worked out by counting, why all the chances add up to 100%, and when to multiply chances and when to add them. About ten minutes.
Froga
What Machine learning 2 builds on: the logic gates again, what makes a neuron fire, what a feature is, and why a perfect score on practice questions can mislead. About ten minutes.
Froga
What Machine learning 1 builds on: what a labelled example is, how a score decides spam or not, what "training" actually changes, and why you keep some examples back. About ten minutes.
Froga
Tokens, parameters, attention, hallucination — the mechanics behind ChatGPT and every model like it, explained once so the vocabulary stops being intimidating.
Froga