
In the next few months, I plan to start a tiny experiment around recursive self improvement. Tiny in that I'm applying RSI to a toy, called DeepMuse. DeepMuse started out as a visual music synthesizer called Sky, which I would perform as a VJ 20+ years ago*.
Underneath was a data flow script, call Flo, which I kept rewriting. And rewriting. And rewriting. It was inspired by my days playing with an analog music synthesizer*. And then designing a project management system with Petri nets. Around that time, was a project at MIT around a Cellular Automata Machine*. And then there was Max*, a node based patcher for musical instruments. They all fostered a mindset, that information is flow.
A few years ago, I attended a workshop at NASA called: "The Virtual Iron Bird"*, which introduced the concept of using an Ontology to wrap the mission critical data flow around a space craft. So, I rewrote Flo again. But not for spacecraft; for visual music.
The goal was to make creating an ontology as fun as patching a modular synthesizer. Where you could plug, play, and experiment. The nice thing about an ontology for a toy is that, in contrast to a space craft, if you get it wrong, nobody dies. Instead, you get something interesting to iterate on. And because it is a toy, the ontology should be something a 12-year-old could understand.
I introduced this idea at a SuperHappyDevHouse* gathering, hosted ironically by Palantir. Ironically, in that I didn't know who Palantir was. It turns that Palantir was also working on ontologies. The kind where people could in fact die. To each their own, I suppose
What I hope to learn from making a Toy RSI is how to create a dialog with a Superintelligence. Not by a specialist; but by anyone, from age 12 on up.
So, here's the prompt I made to OpenAI, Anthropic, Grok, and Google, with a follow-up asking Why:
I want to implement recursive self improvement (RSI) on decomposing source code into a small flo ontology, called MuFlo. The tools I want to use are: Apple Studio M5 Ultra 512 GB, open weight models to decompose DeepMuse project, close source models from OpenAI, Anthropic, and Google, to debate best implementations. See https://github.com/musesum/DeepMuse for toy application and package references to MuFlo.
Why, in short:
Do RSI on DeepMuse because it is a real, complex, evolving codebase that can serve as both training material and a hard test for MuFlo.
The purpose is to see whether repeated AI-driven decomposition can:
So DeepMuse is not the end product. It is the experimental substrate for discovering whether MuFlo can become a smaller, more general executable representation of software.
Why: a synth with thousands of parameters is useless if only the author can play it.
Digital audio copied analog patching and then broke it. MIDI is 0–127, a screen is 1920×1280, an accelerometer is ±3g. Without auto-remap, every cable is a unit conversion. Without a loop-break (Visitor / GABA), a live graph eats itself. Without twins, two devices are two programs.
MuFlo is the why of size. Nine primitives, not a tenth. If it cannot be said with Node, Tree, Graph, Plugin, Value, Wildcard, Twin, Closure, Visitor, it is not decomposed yet. A 12-year-old never sees that — they see things, pipes, knobs. “Connect my thumb to brush size.”
The Swift/Metal grew anyway. RSI is the why of keeping the ontology: rewrite source until the graph is smaller than the code and still plays. Open weights on the Studio own the tree so DeepMuse never leaves the box. Closed models only argue. The chair merges.
Playable, local, small. That is the whole why.
ARCHITECTURAL DRIVERS: DEEPMUSE TO MUFLO DECOMPOSITION