Show of Hands is a screen-printed drawing of raised hands — but it was not drawn by a person reaching for a subject. It was grown by an algorithm searching for an image that a dozen separately trained neural networks would all recognize as the same thing.
The work builds on Rosetta neurons: individual units that, across networks trained independently on different data and objectives, fire on the same visual structure — a rare point of agreement between otherwise incommensurable machine minds. I located a neuron for raised, open hands shared across twelve vision models (self-supervised, contrastive, and reconstruction-trained, spanning a 460× range in size), then used an evolutionary optimizer to evolve a two-ink drawing that drives that shared neuron as hard as possible. Where the source images showed hands holding signs or lanterns, the optimizer discarded the held objects and drew only the hands: the concept the machines hold in common is the gesture itself.
The resulting form activates the concept not only in the twelve models it was optimized against, but in models held out from the search — and even in a network trained exclusively on photographs of plants and animals, which has no reason to know human signage yet still reads the gesture. The animation above lights the print as each model sees it: the glow drifts and settles, one network at a time.