VIBEFLY
i trained a fly to code.
unfortunately, he's a vibe coder.
Real fly wiring. An AI assistant. Paid in bananas.
3 bananas × €2 = €5. That can't be right.
CIRCUIT RESPONSE awaiting task
“works on my machine”
— a literal bug
The neural readout picks the action. The AI writes the patch. The tests decide whether he gets paid.
Okay, what is actually happening here? +
How the controller works
We adapted DesktopFly's 1,045-neuron MaleCNS locomotor circuit, keeping its 17,224 measured connections fixed. An artificial encoder turns software status into sensory currents. A reward-trained action policy is distilled into a linear readout of the circuit's simulated spikes.
This page reruns the circuit locally, chooses actions from the trained readout, applies a previously recorded Codex patch, and evaluates the arithmetic tests in your browser. The fly's typing is animation. The large brain is measured anatomical context, not a claim that the whole brain is running.
Synthetic workflow trials: 500 episodes per training seed, three seeds. The simulator supplies patches with an 82% repair probability. These are workflow results, not coding-benchmark scores. A handwritten workflow performs comparably; this does not establish a biological or native-wiring advantage. The three recorded code repairs are separate evidence.