Performance Generator

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:

In this performance art piece, the artist will literally be in her own show. She will be asleep in a gallery space for the duration of the show. She will be presented with everyday mundane objects and will have to incorporate them into one of her pieces of artwork.



“I am hoping that this piece will force the viewers to realize that even the most mundane object can be an interesting piece of art in the hands of a master. I’m hoping to make the viewers realize that even something as simple as a dish can be an excellent piece of art, if it’s done correctly.”

The projected images on the wall behind the artist will be moving at a speed slightly slower than normal. The images will be of the artist’s surroundings, but with the speed of the image being slowed down, the viewer will be able to see everything that happens in the gallery space.

The artist will be sleeping for the duration of the entire performance.

The gallery space will be covered with tarp that is painted to look like the walls of the gallery. This way, nothing will be able to be taken out of the gallery. The gallery will be cleaned with a disinfectant to keep the artist healthy.

The gallery will be locked so that nobody can come in.

When the artist is sleeping, the images on the wall will be very distorted and distorted audio from the gallery space will be played.

The gallery will be lit with red lights to give a spooky feel to the performance.