Chapter 0 · Start here
The AI learning path
AI is software that learns patterns from examples instead of following only hand-written rules.
Chapter 0 · Start here
AI is software that learns patterns from examples instead of following only hand-written rules.
More than 80 years of ideas, from early neural networks to reasoning, coding and computer-use agents. Start with the foundations, then explore how they combine in modern workflows.Selected recent examples: ChatGPT agent (2025) · GPT-6 Sol and Luna (2026).
Start with what AI is and how machines learn.
Start: What is AI? →Each concept is one short lesson. They go in the order the ideas appeared, so you never meet a word you have not learned yet.
What AI is, in plain words, and how this course works.
The first ideas: artificial neurons, the Turing test, the word 'AI', and the winters.
How machines learn from data: models, loss, training and testing.
Neurons, weights, layers and how networks learn with backpropagation.
GPUs, ImageNet, convolution, word vectors and the networks that changed everything.
Tokens, vocabularies, embeddings and vectors: how text becomes maths.
The 2017 architecture behind every modern language model.
Next-token prediction, pretraining, scaling, and how an LLM writes.
From a raw text predictor to a helpful, honest, harmless assistant.
How to ask well, and how to give a model the right information.
Practical habits for work, study and home, for everyone.
Giving models fresh, private and checkable knowledge.
From chatbots to AI that takes actions.
Models that think before they answer.
AI that sees, hears, speaks and creates media.
Hardware, speed, cost and AI on your own device.
AI that folds proteins, moves robots and learns how the world works.
Fairness, privacy, safety, law and where AI is heading.
Step-by-step tutorials to run and use AI models on your own computer.
Build RAG over your PDFs, a local vector database, an MCP server, a small agent, and train and fine-tune models.
Speech, images, data extraction, a web page for your app and more, on your own computer.