lens
five courses · seven chapters each · two depths

The fundamentals of machine learning, at the depth you choose.

The ideas that were true in 1990, are true now, and will still be true in 2050 – with the mechanism running live on the page rather than screenshotted onto it.

The ladder

each rung earns the next

Primer

A gentle on-ramp – Curious mode only
0
AI PrimerCurious

Seven chapters of pure on-ramp – what a model is, how it learns from examples, and why a chatbot is a prediction machine rather than a mind. No equations anywhere.

No prerequisites
Start

Foundations

The machinery every model is built from
I
The Maths of LearningCuriousStudent

Vectors, matrices, derivatives, gradients, probability and entropy – each one introduced at the moment a machine-learning mechanism needs it, and landing on that mechanism running live.

Start here
Start
II
Machine LearningCuriousStudent

What a model is, what it means to be wrong, how being-less-wrong becomes a procedure you can run – and why scoring well on the data you trained on proves nothing at all.

7 chapters · in review
III
Neural NetworksCuriousStudent

From a single artificial neuron to a trained network – what one unit computes, why stacking them buys expressiveness, how backpropagation assigns credit, and what depth actually learns.

7 chapters · in review

Core

Where the pieces become a language model
IV
Language ModelsCuriousStudent

Tokens, embeddings, attention as a data-dependent weighted average, the transformer block, and how a distribution over next tokens becomes text. The mechanism, not the product.

7 chapters · in review

Deep dives

one idea, one pageView all 1 deep dive
LanguageComing soon
Why attention is quadratic
Where the n-squared bill in attention actually comes from, why you meet it as a context window, and the standard escape families, priced by what each gives up.
Referenced in Language Models

Tools

the tool is the destination
What is this? · About the project →