read · learn · build

113 articles. 15 stages. One coherent path.

The theory side of the site — the full organized/ learning path, vendored for offline-friendly publishing. Each article cross-links to the hands-on companion track that turns the theory into running code. Browse below, or open the curriculum view if you'd rather have a starting line picked for you.

113
articles
16
stages
7h 45m
of reading
if you read three things, read these

Editor's picks

path overview

Read me first

Top-level docs that frame the path itself.

jump to a stage

Browse by stage

01

Math Foundations

Linear algebra, probability, calculus, info theory.

02

Ml Fundamentals

Supervised, unsupervised, evaluation, regularization.

03

Neural Networks

Backprop, activations, optimizers, regularization.

04

Language Modeling

n-grams to RNNs to why transformers won.

05

Tokens Embeddings

How text becomes vectors.

06

Transformers

Self-attention, multi-head, KV caching, GPT from scratch.

07

Modern Llms

Scaling laws, MoE, reasoning models, long context.

08

Prompting

Few-shot, CoT, structured outputs, sampling.

09

Rag

Chunking, embeddings, hybrid search, reranking, evals.

10

Fine Tuning

SFT, LoRA, RLHF, DPO, GRPO, embedding fine-tuning.

11

Agents

Loops, tools, memory, planning, multi-agent, browser/vision.

12

Multimodal

CLIP, VLMs, diffusion, video, speech, synthetic data.

13

Production

Deployment, evals, guardrails, observability, cost, data systems.

14

Applications

Text-to-SQL, code, browser agents, finance, case studies.

15

Engineering Career

Roles, learning roadmap, staying current.

exercise_solutions