Skip to content
kevinferron.com

Lab · Minds · A series of recordings · Interactive, in your browser

agent-neuron

An agent-neuron is a wrapper, and whatever goes inside it (a model, a shell script, a small function or a person) gets the same interface, so any neuron can send to any other. They connect many to many, so what you end up with is a graph, not a pipeline, and nothing in the middle decides when a neuron acts: its own wrapper does. This series plays back recordings of small networks I built to test the idea, one behaviour per chapter. Nothing on these pages runs live.

So what you see already happened, on one clock.

What this series is not

  • A live run. Every figure plays a recording made once on one machine. No model is called. Nothing leaves your browser.
  • A benchmark. The numbers come from one run. The data is invented.
  • A model of the brain. “Neuron” is a loose name. It names connective tissue between programs.
  • A product. It isn’t for sale.

Chapters