[Karim’s short framing intro — the "see what I’m building" invitation — comes here]
Monopoly Machine
Why does the game always end with one winner? An economics sandbox with taxes, inheritance, UBI and jubilees — change the rules, watch what happens.
Weasel
Dawkins’ cumulative selection, live: from random letters to a line of Shakespeare in about sixty generations.
MENACE
A tic-tac-toe machine made of matchboxes and beads that learns to win — 1960s machine learning, rebuilt in your browser.
nano-Karim
A tiny language model trained from scratch on my own writing — watch it learn, attempt by attempt, to sound like me.
nano-Shakespeare
The same tiny model, raised on Shakespeare instead. Compare what a diet of words does.
Routing Apprentice
A neural network teaches itself delivery-van routing by trial and reward — and edges out the classic textbook method.
Cash-Flow Game
An AI bookkeeper learns which invoices to pay early and which to stretch — and beats three benchmark strategies.
Connect Four (AlphaZero-lite)
Self-play only, no human examples: a miniature AlphaZero that made itself effectively unbeatable overnight.