Learn it.
Practice it.
Achieve Mastery.
How AI works, from linear algebra and gradient descent to transformers, RAG, and agents. Each idea is explained step by step, and most come with a Python problem you solve in the browser and check against test cases.
254 pages and 243 practice problems.
Tokens attend to tokens
Q · Kᵀ / √d → softmax → weighted values, computed in the page.Q · Kᵀ / √d scores normalized with softmax
Read it, poke at it, then write it.
- An explanation that starts from what you already know and says where the idea breaks down.
- Where it helps, a diagram or widget you can change and watch the numbers move.
- A practice problem: write the function yourself and run it against the tests.
The control loop of a graph-based agent. Interactive version
Seven sections, in reading order. Start wherever you need to.
Foundations
Python, systems basics, and the math the rest of the site leans on.
19 pages
02Models
Classical ML, deep learning, vision, NLP, speech, LLMs, graph ML, and RL.
86 pages
03Agents & Applications
Agents, and AI applied to science, healthcare, and other domains.
26 pages
04Systems & Infrastructure
Designing, shipping, and running ML systems: MLOps, databases, frameworks.
59 pages
05Safety & Evaluation
Evaluation, security, alignment, and interpretability.
18 pages
06Research & Build
Reading papers, building models from scratch, and full projects.
28 pages
07Career
Interview prep, roadmaps, and resources.
17 pages