Posts
Every entry, newest first.
- № 010
A task scheduler from scratch
Sixty tasks that wait for one another, four workers, 215 lines of TypeScript. The scheduler itself is four rules, failed tasks and all; the hard part is answering "how long is left". Watch three progress bars mislead you, then use the scheduler to forecast itself, and let it learn from the tasks that have finished.
Interactive#ai-agent#from-scratch
10 min - № 009
A city nobody schedules — 300 people, each minding their own needs
A procedurally generated 3-D city where every person picks the next thing to do from four needs of their own. Swap the deciding for dice or a fixed timetable and watch the rhythm of the whole city change.
Interactive#ai-agent#from-scratch
10 min - № 008
Drawing the map while finding yourself on it — SLAM from scratch
A small car with no GPS and no map has to draw the map and find itself on it at the same time. Drive it round a loop, watch its map bend, and watch the whole thing snap straight the moment it gets back to where it started.
Interactive#ai-agent#robotics#from-scratch
8 min - № 007
How a cloud of noise becomes an apple: training a 3-D diffusion model in the browser
Pick two fruit and press Train. A diffusion model written from scratch learns, in your browser, to pull a cloud of coloured 3-D noise into those two fruit, colours included. Then we take apart what it learned.
Interactive#generative#diffusion#from-scratch
11 min - № 006
A robot dog in the browser: its walking policy is four matrix multiplications
MuJoCo compiled to WebAssembly plus the walking policy Deep Robotics published make a Lite3 walk in your browser. Then you try to knock it over: blindfold its senses, shove it, detune its motors.
Interactive#ai-agent#robotics#reinforcement-learning
9 min - № 005
One body, two heads: training a HydraNet that draws boxes and masks, in the browser
Emoji fruit as training data, and a small network with one shared trunk and two output heads, trained from scratch in your browser. It finds the fruit within ten seconds. Then we measure honestly what multi-task learning bought us and what it cost.
Interactive#computer-vision#multi-task#from-scratch
11 min - № 004
Training a Transformer from scratch in the browser: watching attention grow
No PyTorch and no libraries. A tiny autodiff engine and a Transformer of about fourteen thousand parameters, written in TypeScript. Press a button and it learns to reverse a string of digits within seconds.
Interactive#llm#transformer#from-scratch
8 min - № 003
Building a neuroevolution trading squad: from gambler to market wizard
Let a crowd of random trading bots compete, breed and mutate on Apple's 2024 share price. After thirty generations they return +43%, against +34% for buy-and-hold. Train one yourself, then see why that number doesn't count.
Interactive#ai-agent#neuroevolution#trading
5 min - № 002
From rookie to boss bird: 50 birds teach themselves Flappy Bird
Give each of fifty birds a brain of only six weights, add survival of the fittest, and usually within twenty-odd generations they clear a hundred pipes in a row. Then open that brain and see what it actually learned.
Interactive#ai-agent#neuroevolution#from-scratch
4 min - № 001
A CNN from scratch: watching a convolutional network see, in your browser
A handwritten-digit classifier written in plain TypeScript with no machine-learning library, then opened up so you can look at the output of every layer.
Interactive#computer-vision#cnn#from-scratch
7 min