Transformer Neural Network Implemented in HyperTalk for Classic Macintosh
By
hammer32
The kind of bagel that ruins lesser bagels for you.
Summary
A complete transformer neural network implemented entirely in HyperTalk, a 1987 scripting language designed for interactive card stacks, running on a Macintosh SE/30. The MacMind project is a 1,216-parameter single-layer single-head transformer that learns the bit-reversal permutation (the opening step of the Fast Fourier Transform) from random examples. It includes all standard transformer components: token embeddings, positional encoding, self-attention with scaled dot-product scores, cross-entropy loss, full backpropagation, and stochastic gradient descent, all written in HyperTalk.
Key quotes
· 3 pulledMacMind is a 1,216-parameter single-layer single-head transformer that learns the bit-reversal permutation -- the opening step of the Fast Fourier Transform -- from random examples.
Every line of the neural network is written in HyperTalk, a scripting language from 1987 designed for making interactive card stacks, not matrix math.
It has token embeddings, positional encoding, self-attention with scaled dot-product scores, cross-entropy loss, full backpropagation, and stochastic gradient descent.
You might also wanna read
Transformer AI Model Successfully Runs on Commodore 64 with 25,000 Parameters
A developer has successfully implemented a 25,000-parameter transformer neural network (the same architecture used by ChatGPT, Claude, and G
github.com·1mo ago
XORTRAN: A FORTRAN IV Neural Network for IBM 1130 and PDP-11 Computers
XORTRAN is a multilayer perceptron neural network written in FORTRAN IV that runs on vintage IBM 1130 (1965) and PDP-11 (1970-1980) computer
github.com·6mo ago
NVIDIA Announces "Hack for Impact" London Event for Autonomous AI Agent Development
NVIDIA is hosting a "Hack for Impact" event in London, challenging participants to build autonomous agentic applications using open-source m
luma.com·3h ago
MerLean-Prover: A Recursive Agent Harness for Lean 4 Theorem Proving Outperforms Baselines
MerLean-Prover is an end-to-end Lean4 theorem prover that replaces 'sorry' declarations with kernel-checkable proofs using three agent types
arxiv.org·4h ago
ZX Spectrum BASIC interpreter rebuilt from scratch to run natively in web browsers
A developer has rebuilt the ZX Spectrum's BASIC interpreter from scratch to run in a web browser, without emulating the original Z80 hardwar
boingboing.net·1d ago
Reflections on DwarfStar 4's rapid rise in local AI inference
The author reflects on the unexpected popularity of DwarfStar 4 (DS4), a local AI inference project. They attribute its success to the conve
antirez.com·1d ago