Show HN: MacMind – A transformer neural network in HyperCard on a 1989 Macintosh (github.com)

by hammer32 42 comments 159 points
Read article View on HN

42 comments

[−] edwin 28d ago
There’s something quietly impressive about getting modern AI ideas to run on old hardware (like OP's project or running LLM inference on Windows 3.1 machines). It’s easy to think all the progress is just bigger GPUs and more compute, but moments like that remind you how much of it is just more clever math and algorithms squeezing signal out of limited resources. Feels closer to the spirit of early computing than the current “throw hardware at it” narrative.
[−] wdbm 28d ago
There is an absolutely beautiful rendering of the Mona Lisa encoded at some point in the digits of pi. If you know the position, it's really easy to plot the image.

But first you have to find that position.

[−] zoky 28d ago
This is both simultaneously false, and true but largely meaningless. If you mean the Mona Lisa is somehow directly encoded somewhere in pi, then of course it’s not. It’s just a number.

If you mean that when you feed the numbers starting with some offset of pi into a specific algorithm you will get a rendering of the Mona Lisa, then yes, but so what? Allow me to introduce you to the PiMona algorithm. I won’t bother you with the implementation details, but it takes exactly one integer parameter. If it’s 3, it produces a beautiful rendering of the Mona Lisa. Anything else and it generates random garbage. Turns out, it’s really easy to find where the Mona Lisa is encoded in pi! It’s right there at the start.

But let’s say you meant that the digits of pi at some offset, when encoded properly and fed into any algorithm that is theoretically capable of generating the Mona Lisa will cause that algorithm to do so, then sure. But that’s also true of random noise, and says more about the algorithm and the nature of random numbers than about the Mona Lisa somehow being encoded into the fabric of the universe (which I’m sure isn’t what you meant, but I’m just saying there’s nothing really special about pi in that regard, except that as far as we know, it continues infinitely).

[−] mfro 27d ago
I think they're going for more of a 'monkeys will eventually produce shakespeare' thing here. Which you can apply the same argument to - monkeys do not know english, don't know what they're typing, and theoretically english could devolve to a state where every sentence could be qualified as shakespeare, right? Your argument just seems unnecessarily pedantic.
[−] hammer32 28d ago
Exactly. Working in a constrained environment invites innovation.
[−] Unbeliever69 28d ago
Now do this on a Casio Watch next :)
[−] hyperhello 29d ago
Hello, if there are no XCMDs it should work adequately in HyperCard Simulator. I am only on my phone but I took a minute to import it.

https://hcsimulator.com/imports/MacMind---Trained-69E0132C

[−] hammer32 28d ago
I had no idea your simulator existed. No XCMDs, correct; everything is pure HyperTalk. I just ran a few training steps and they complete in a second or two. Thank you for importing it!
[−] hyperhello 28d ago
I gotta ask. Your scripts have comments like -- handlers_math.hypertalk.txt at the top. Are you using some kind of build process for a stack?
[−] hammer32 28d ago
More of a copy-paste process. The scripts are written as .txt files in Nova on my Mac Studio, then pasted one at a time into HyperCard's script editor on the classic Mac. The files are kept separate because SimpleText has a 32 KB text limit.
[−] hyperhello 28d ago
As an alternative, you might consider letting Hypercard itself open the text files and 'set the script of' as needed.
[−] hammer32 28d ago
Yup, that would have been easier. It's been decades since I've done anything with HyperCard. I had to re-take the built-in intro course again :)
[−] jasomill 28d ago
Would that overcome the size limit?

Does HyperCard implement its on text handling for the HyperTalk editor that doesn't rely on the TextEdit toolbox service (which IIRC is the source of SimpleText's 32 kB limit)?

[−] hyperhello 28d ago
Fields appeared to use TE and I suppose the script editor was pretty much limited to 32 kB of text for that reason, although you could have any size of text in a variable.
[−] jasomill 28d ago
Curiousity got the better of me, and I just tested it in Infinite Mac.

The HyperTalk editor is indeed limited to 32 kB.

It's certainly possible that this limit only applies to editing scripts, as it's unlikely TextEdit was used in the process of interpreting them, but I don't have time tonight to investigate.

Later versions of HyperCard supported OSA scripts as well, now I'm also curious what the size limit is for (presumably) compiled AppleScripts stored in HyperCard stacks.

[−] watersb 28d ago
This is great!

I first studied back-propagation in 1988, at the same time I fell in love with HyperCard programming. This project helps me recall this elegant weapon for a more civilized age.

[−] hammer32 28d ago
Building this definitely felt like constructing a lightsaber from spare parts: slow, deliberate, but it works and you understand every piece of it.
[−] nxobject 28d ago
I love this. From reading the nuts-and-bolts "parameters" (haha) of your implementation, I get the impression that the fundamental limit is, well, using a 32-bit platform to address the sizes of data that usually need at least 48 bits!
[−] hammer32 28d ago
Thanks! The precision was a happy surprises, HyperTalk uses Apple's SANE library, which gives you 80-bit extended precision. The interpreter speed and the lack of arrays were a challenge. Rediscovering what HyperCard could do was half the fun of this project.
[−] gcanyon 29d ago
It's strange to think how modern concepts are only modern because no one thought of them back then. This feels (to me) like the germ theory being transferred back to the ancient greeks.
[−] hammer32 29d ago
Right? Backprop was published in 1986, a year before HyperCard shipped. Attention is newer, but a small model like this was buildable.
[−] anthk 29d ago
Lisp is from 1960's and with s9 you can do even calculus with ease, in an interpreter small enough to fit in two floppies.

On the Greeks, Archimede almost did 'Calculus 0.9'.

[−] jeffbee 28d ago
People did think of many of these core concepts decades ago, but they did not have the resources to put them into practice.
[−] kdhaskjdhadjk 29d ago
I think it's incredible to see the potential that is still locked up in old hardware. For example the 8088 MPH demo. Amazing what he was able to do with an 8088 and CGA. All this time the hardware had that potential, but it took decades to figure out how to unlock it, long after the hardware was considered obsolete. Imagine the sort of things that might be done later down the road with hardware of 0-20 years ago if somebody really dug into it to that level.
[−] tty456 28d ago
Where's the code for the actual HyperCard and building of the .img? I only see the python validator in the repo.
[−] rcarmo 28d ago
Neat. Looks like I found my new benchmark for my ARM64 JIT for BasiliskII :)

(still debugging it, but getting closer to full coverage)

[−] DetroitThrow 29d ago
This is very cool. Any more demos of inference output?
[−] immanuwell 28d ago
The architecture of macmind looks pretty interesting