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 piece:

“The performer should have in her possession a copy of the document on which the performance is based, a sign that reads ‘CHANGE’ and a book of matches. She should also have the means for making a copy of the document on which the performance is based, for example a photocopier or a scanner. The performance should be held in a place that is not open to the public, such as an office or a private house. The performer should not perform the instructions in the presence of anyone else. The performance should be recorded on a video camera by the performer herself. The performance should end with the performer burning a copy of the document on which the performance is based.”

Anon. (1995).