A field guide to large language models
What's inside
Reading, until it actually sticks
Three tools woven through every chapter — an AI reviewer for your code, a tutor that re-explains anything you skim, and quiet progress tracking so you always know where you left off.
Feature
AI code review
Submit a solution, get a focused critique — correctness, style, complexity — in seconds.
def softmax(x):
e = np.exp(x - x.max())
return e / e.sum()
All 5 tests passed
Numerically stable. Consider axis=-1 for batched inputs.
Feature
On-demand AI tutor
Stuck on a paragraph? One click and a tutor re-explains it with more intuition, more math, or a fresh angle.
Q · What is attention?
Attention weighs tokens by relevance.
Feature
Progress tracking
Chapters read, questions understood, problems solved — quietly tracked as you go.
Chapter 013/4
- Tokenization
- Attention
- Positional encodings
- Layer norm
The syllabus
Everything, in five parts
A guided path from the transformer block out to the research frontier. Every chapter pairs a deep read with practice and a first-class coding tab.
Part I
Foundations
3 chaptersPart II
Pretraining & Scale
4 chaptersPart III
Post-Training & Alignment
5 chaptersPart IV
Systems & Serving
2 chaptersPart V
Frontiers
3 chaptersStart at the beginning
Chapter 01 — Transformer Architecture Internals.