Doodles
Visual guides to how AI actually works
Complex ideas, drawn out plainly. Less boring than documentation, more accurate than a fever dream. Free to read, easy to share.
01
How LLMs Work
Tokenization, attention, and why your chatbot sometimes sounds drunk.
Read →
02
The Seahorse Problem
Why AI confidently makes things up — and how to catch it in the act.
Read →
03
The Biased Mirror
How AI absorbs and amplifies human prejudices, and what we can do about it.
Read →
04
Token Gesture
The hidden currency of AI — why your words get chopped up and cost money.
Read →
05
Build Your Own LLM
Paste text and watch a mini language model learn patterns. Interactive demo.
Try it →