Learn · everything here is free

Learn

Every learning resource on this site, organized by what you want to do. Start anywhere.

01 · Understand how AI works

The Field Guide

524 terms · 8 regions · 61 landmarks

A map of AI, not a syllabus. Pick any destination and follow a route through exactly the ideas you need first, basics first.

  • Foundations
  • Neural Networks
  • Training
  • Evaluation
  • Language & LLMs
  • Vision & Multimodal
  • Agents & RL
  • Shipping AI
Open the map

Or jump straight to a destination

8 stops to get there Transformer A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model. 20 stops to get there RLHF Reinforcement Learning from Human Feedback - training models using human preferences to align behavior with human values. 18 stops to get there Retrieval-Augmented Generation Augmenting LLM generation with retrieved relevant documents, improving factuality and enabling knowledge updates without retraining. 2 stops to get there Diffusion Model A generative model that learns to denoise data, achieving state-of-the-art image generation (Stable Diffusion, DALL-E 2).

Papers · 36 canon · 100 frontier

The research behind the map

The all-time papers worth knowing and last year's most-cited, each in plain words, with the Field Guide ideas to read first.

02 · Build with coding agents

Play it, then take it apart

Play · 90 seconds

The Duel

Feed 12 real jobs to one frontier model and watch $31 of context burn. Then ship them all for $3.07.

10× cheaper

Course · 5 animated lessons

Agentic Coding Harnesses

How coding agents actually work, taken apart: DeepSeek Harness, opencode, Kimi Code CLI, Pi.

5 lessons

Guide · 10 concepts

Claude Guide

Hooks, subagents, memory, MCP, skills and more: Claude Code concepts, each explained with an animation.

10 concepts

03 · Keep up

The blog

Latest · September 22, 2025 · 2 posts

The Evolution of Developer-Targeted Recruitment Scams: From Fake Profiles to Spoofed Commits

How sophisticated social engineering attacks exploit developer trust through fake LinkedIn profiles, spoofed GitHub commits, and malicious npm packages. Learn how to protect yourself from these multi-layer attacks.

 All posts →

New lessons, first

Get the next one when it ships.

New lessons, Field Guide deep dives and posts, one email at a time. Free, no spam.