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:

A woman is lying on a couch. She is wearing a long, white, loose-fitting nightgown. There is a small table beside the couch with a candle on it, and a glass of water. A man in a suit is sitting on a chair beside the couch. They talk casually for a while, then the man gets up, walks to the table, and blows out the candle. The woman on the couch says nothing. The man walks back to the chair and sits down. The woman gets up, still saying nothing, and walks to the table. She takes a sip of water, and then a long drink. She walks back to the couch, and lies down again. She does not speak. The man gets up, walks to the table, blows out the candle, and walks back to the chair. The woman sits up, gets up, walks to the table, takes a sip of water, and a long drink. She walks back to the couch, picks up the glass, walks back to the table, puts the glass back down, and walks back to the couch. She sits down.