MacMind is a complete transformer neural network, embeddings, positional encoding, self-attention, backpropagation, and gradient descent, implemented entirely in HyperTalk, the scripting language Apple shipped with HyperCard in 1987. Every line of code is readable inside HyperCard's script editor. Option-click any button and read the actual math.
The task: learn the bit-reversal permutation, the opening step of the Fast Fourier Transform. The model has no formula to follow. It discovers the positional pattern purely through attention and repeated trial and error. By training step 193, it was oscillating between 50%, 75%, and 100% accuracy on successive steps, settling into convergence like a ball rolling into a bowl.
The whole "intelligence" is 1,216 numbers stored in hidden fields in a HyperCard stack. Save the file, quit, reopen: the trained model is still there, still correct. It runs on anything from System 7 through Mac OS 9.
As a former physics student, and the FFT is an old friend, it sits at the heart of signal processing, quantum mechanics, and wave analysis. I built this because we're at a moment where AI affects all of us but most of us don't understand what it actually does. Backpropagation and attention are math, not magic. And math doesn't care whether it's running on a TPU cluster or a 68030 from 1989.
The repo has a pre-trained stack (step 1,000), a blank stack you can train yourself, and a Python/NumPy reference implementation that validates the math."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: MacMind \u2013 A transformer neural network in HyperCard on a 1989 Macintosh"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/SeanFDZ/macmind"}},"_tags":["story","author_hammer32","story_47792525","show_hn"],"author":"hammer32","children":[47793913,47794116,47794274,47796643,47797671,47798457,47799687,47800258,47801063],"created_at":"2026-04-16T13:16:29Z","created_at_i":1776345389,"num_comments":42,"objectID":"47792525","points":159,"story_id":47792525,"story_text":"I trained a transformer in HyperCard. 1,216 parameters. 1989 Macintosh. And yes, it took a while.
MacMind is a complete transformer neural network, embeddings, positional encoding, self-attention, backpropagation, and gradient descent, implemented entirely in HyperTalk, the scripting language Apple shipped with HyperCard in 1987. Every line of code is readable inside HyperCard's script editor. Option-click any button and read the actual math.
The task: learn the bit-reversal permutation, the opening step of the Fast Fourier Transform. The model has no formula to follow. It discovers the positional pattern purely through attention and repeated trial and error. By training step 193, it was oscillating between 50%, 75%, and 100% accuracy on successive steps, settling into convergence like a ball rolling into a bowl.
The whole "intelligence" is 1,216 numbers stored in hidden fields in a HyperCard stack. Save the file, quit, reopen: the trained model is still there, still correct. It runs on anything from System 7 through Mac OS 9.
As a former physics student, and the FFT is an old friend, it sits at the heart of signal processing, quantum mechanics, and wave analysis. I built this because we're at a moment where AI affects all of us but most of us don't understand what it actually does. Backpropagation and attention are math, not magic. And math doesn't care whether it's running on a TPU cluster or a 68030 from 1989.
The repo has a pre-trained stack (step 1,000), a blank stack you can train yourself, and a Python/NumPy reference implementation that validates the math.","title":"Show HN: MacMind \u2013 A transformer neural network in HyperCard on a 1989 Macintosh","updated_at":"2026-09-28T05:04:48Z","url":"https://github.com/SeanFDZ/macmind"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["gradium"],"value":"gradus_ad"},"title":{"matchLevel":"none","matchedWords":[],"value":"Philip Low Unmasking Musk"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://bsky.app/profile/brainking.bsky.social/post/3lgsco7cdnc26"}},"_tags":["story","author_gradus_ad","story_42903336"],"author":"gradus_ad","children":[42903550,42903587,42903678,42903703,42903865,42904069,42904167,42904188,42904205,42904266,42904312,42904346,42904537,42904546,42909710,42920606,42981505,42981514],"created_at":"2025-02-01T22:54:04Z","created_at_i":1738450444,"num_comments":70,"objectID":"42903336","points":222,"story_id":42903336,"title":"Philip Low Unmasking Musk","updated_at":"2026-09-28T04:27:04Z","url":"https://bsky.app/profile/brainking.bsky.social/post/3lgsco7cdnc26"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["gradium"],"value":"radius89"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["gradium"],"value":"Hello HN!
I'm relaunching Radius [1] - far too long after the original Show HN [2] (I'll blame the day job for that).
Radius started out from my frustration with not knowing what was going on around me. The initial plan was to "show all and every type of event" from big to small, but over time I narrowed the focus to communities, groups, events, and helping people connect through them.
The initial Show HN gave me 150+ comments (surprising, looking back, given how terrible the plain Bootstrap UI was...) with a huge amount of useful feedback and feature requests. I've spent the time since then working through that, along with additional requests from groups using Radius, and it finally feels ready for a proper relaunch.
I've also recently added "Activities" [3] - which are lightweight events, independent of groups, intended to help people find others to do things with - for example:
> John is going for a cycle and a coffee in New York at 10am
People can join and vote for a time that works for them.
I've got a bunch of ideas for where to go next with this, including things like open sourcing and federation, but those are for another day!
Any feedback would be greatly appreciated!
P.S. it's built with Ruby on Rails, for those interested. I highly suspect it would have taken me 2 more years to get to this point without Rails!
[2] https://news.ycombinator.com/item?id=40717398
[3] https://radius.to/documentation/activities/post-an-activity"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["gradium"],"value":"Show HN: Radius \u2013 A Meetup.com Alternative"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["gradium"],"value":"https://radius.to/"}},"_tags":["story","author_radius89","story_49777539","show_hn"],"author":"radius89","children":[49777741,49777809,49777835,49777854,49777860,49777883,49777964,49778032,49778201,49778209,49778446,49778462,49778575,49779998,49780153,49780216,49780476,49780504,49780791,49780878,49781183,49782191,49782534,49782842,49783020,49783534,49783566,49783631,49783913,49786349,49787175,49790891,49791632,49804916,49809160,49818122],"created_at":"2026-09-20T16:51:26Z","created_at_i":1789923086,"num_comments":87,"objectID":"49777539","points":169,"story_id":49777539,"story_text":"Hello HN!
I'm relaunching Radius [1] - far too long after the original Show HN [2] (I'll blame the day job for that).
Radius started out from my frustration with not knowing what was going on around me. The initial plan was to "show all and every type of event" from big to small, but over time I narrowed the focus to communities, groups, events, and helping people connect through them.
The initial Show HN gave me 150+ comments (surprising, looking back, given how terrible the plain Bootstrap UI was...) with a huge amount of useful feedback and feature requests. I've spent the time since then working through that, along with additional requests from groups using Radius, and it finally feels ready for a proper relaunch.
I've also recently added "Activities" [3] - which are lightweight events, independent of groups, intended to help people find others to do things with - for example:
> John is going for a cycle and a coffee in New York at 10am
People can join and vote for a time that works for them.
I've got a bunch of ideas for where to go next with this, including things like open sourcing and federation, but those are for another day!
Any feedback would be greatly appreciated!
P.S. it's built with Ruby on Rails, for those interested. I highly suspect it would have taken me 2 more years to get to this point without Rails!
[2] https://news.ycombinator.com/item?id=40717398
[3] https://radius.to/documentation/activities/post-an-activity","title":"Show HN: Radius \u2013 A Meetup.com Alternative","updated_at":"2026-09-28T06:24:50Z","url":"https://radius.to/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"2Ucoder"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["gradium"],"value":"Bug: Border radius has infected VSCode editor"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/microsoft/vscode/issues/338035"}},"_tags":["story","author_2Ucoder","story_49848838"],"author":"2Ucoder","children":[49849444,49849581,49849637,49849648,49850138,49850196,49850223,49850321,49850333,49850459,49850565,49850980,49851189,49852566,49853736,49855382],"created_at":"2026-09-25T19:27:37Z","created_at_i":1790364457,"num_comments":51,"objectID":"49848838","points":80,"story_id":49848838,"title":"Bug: Border radius has infected VSCode editor","updated_at":"2026-09-28T02:28:48Z","url":"https://github.com/microsoft/vscode/issues/338035"}],"hitsPerPage":50,"nbHits":23,"nbPages":1,"page":0,"params":"query=Gradium&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":15,"processingTimingsMS":{"_request":{"queue":446,"roundTrip":23},"afterFetch":{"format":{"highlighting":1,"total":1}},"fetch":{"query":13,"total":14},"total":15},"query":"Gradium","serverTimeMS":463}