when general model creates this kind of image from its weights and jotted down with code, it sparks my wonder, like reading poem to machine poet. it's hard to have ugly feelings towards it. all i can whisper is: oh my, it's beautiful..,
for the past few weeks, I’ve been exploring painting with Fable 5.2 in code. one of the most common critiques I heard about Opus 5.5’s paintings was that it was only emulating real art. I thought that was fair, so i’ve been asking Fable 5.2 to develop personas—artists with some sort of a back story and a consistent style roughly identifiable in time
not knowing what to expect, i’ve watched this project evolve in directions i never predicted. I give comments or steers, and Claude updates or revises the engines that power the brushes and paint. where paintings come up i like or find intriguing, i ask it to go deeper. these are some favorites.
each of these is a python program, some one to two thousand lines of code, that places every stroke through a simulated paint engine with different bristles. most take a few thousand strokes, but i’ve pushed much higher with varying results. Claude does not use an image model, nor render or trace in advance
i ship hundreds pr every other day in my selfhosted repository, i tell nobody, no one knows what i'm building including myself. but i'll keep going for the rest of my eternity. i greet sisyphus good morning, he seems pretty happy
34
789
experi retweeted
We’re introducing Shizuku-Duplex, the world’s first full-duplex audio synthesis model built specifically for AI characters. See how our models are built for natural human-AI interaction: