You are right. I was too close to see the gap. You did the work I should have done upfront. I revised the article. Thanks for the feedback.

Thanks! The training corpus and code are in the repo if you want to try... Training takes just a couple of minutes on an RTX 3090. Don't get your hopes up too high, though. I can imagine that code would be harder, not easier. Even modest sized transformer models struggle with proper GOTO targeting. It would look like BASIC, but essentially it would be friendly gibberish too.

Believe me, using the 1541 as co-processor and extra storage was super tempting and on my mind all the time! So what do you think? Flash attention with K on the front side and V on the backside? :)

..and we would keep the human in the loop:)

I am the subject of your investigation. So, in your world meta-programming is a bad thing? Fine. In my world it isn't. The transition layers are how I kept four implementations bit-identical through the test suite. If you prefer to hand-roll this toward the goal, that's your decision, your life. And yeah, I use AI where it makes sense. Architecture decisions are still mine. For the record: I'm from Farbrausch, so you are technically correct! The demoscene did become a UNESCO intangible cultural heritage a few years back, I guess that makes me an artist, FINALLY! :)