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:

Instructions for a performance art work: “To Shoot a Rifle, You First Need a Rifle.”

In this performance, the artist will shoot a rifle at a blank wall and then sift through the rubble for fragments of the bullet and rifle cartridges. She will then use the found bullet fragments and cartridges to construct a new rifle which she will use to shoot at the wall again. This procedure will be repeated until the artist has used up all of the ammunition. During the performance, the artist will record the sound of each shot that she fires on audio tape, so that she can later play it back and listen to her shots echo. The tape will also serve as a reminder of the artist’s performance.