This page will allow you to generate your own instructions for performance art pieces in the style of our current exhibit Embodying the Algorithm using GPT-3’s DaVinci model. Each time you refresh this page, a new performance that has been previously generated using GPT-3 will be displayed. If you would like to record and submit your own performance based on one of the generated texts, please see the instructions on our Submissions page.

Refresh Page to Generate a New Performance

Instructions for a performance by GPT-3:

An idea for performance art: A young woman combs her long blond hair in a department store window. No, the act is not autonomous but part of the store’s display. She is art. No one knows her name, the name of the store, or even the city of the store. She could be anywhere in any country in the world, or more than one. This knowing would extend or enhance our enforced lack of knowledge of its roots. But like Star Wars, we could easily assume the form of this performance. “Weaving Perfection” (1972/1973), by Carolee Schneemann: A female uncovering her thread with an elegant, danceable, and formalised movement could function as a paragon for the model and dancer.