He trained an AI on 140-character demos and taught it his own taste
I post trained a model on Demoscenes
Fascinated by how demoscene effects evolve, the author fine-tuned Qwen2.5-Code-7B on 25k Dweets — 140-character JavaScript demos from Dwitter.net. Continued pretraining cut perplexity from 28.63 to 8.57, and a curriculum favoring highly rated dweets made outputs far more visually interesting. Then, acting as his own reward function in GRPO-based RLHF, he hand-picked favorites from roughly 40,000 rendered animations to inject his aesthetic. Demoscener-7B is on HuggingFace.
Somewhere around the 10,000th animation, I began to appreciate the existence of VLMs and HPSv3. Sadly, it was too late.
- emptybits
The human side of the demo scene is what I think makes it appealing. Sharing and consuming. A fellow human did that! Coder-as-problem-solver-and-artist.
For sure it’s intellectually interesting if AI can generate something novel within demoscene constraints (140 chars or extreme low res or a POKEY chip at 1MHz or whatever) … something humans maybe thought impossible … like a winning move that makes a go or chess grandmaster say WTF. It changes what’s possible. But then most of us (?) still hope the sport/scene/art goes back to human endeavour.
I’ve been to parties where demos are running on a large screen, even ones we’ve seen before, and the audience will ooo and aah because a human figured out how to do that stuff under constraint. The magic is lost if it’s generated IMO.
- InvisibleUp
I think you misunderstand the point of the demoscene. It’s about mathematical prowess and the joy of puzzle-solving moreso than pretty pictures.
Appropriate uses for AI could be to trace the history of demoscene effects, or to explain how a particular scene works so you can understand it better. Nobody in the scene wants a magic box that solves the puzzle for them.
- xg15
Not to be confused with training a model on Demoscenes, the little-known cousin 3rd degree of Greek statesman Demosthenes.
- xacky
Demoscenes are a uniquely human endeavour.
- psenough
congratulations on rediscovering genetic algorithms in procedurally generated art. why learn the math and size coding optimizations that make the effects possible when you can just throw tokens at it and spend time filtering the garbage for the machine? what a time to be alive!