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 a performance art piece: A man dressed as a clown, standing on a stage. A spotlight is trained on the man’s face. A full orchestra plays Mozart’s Requiem in the background. The music swells with tension and an aura of dread. The audience waits for the clown to do something outrageous: pull out a gun, start juggling grenades, go into a screaming rage. The clown just stands there. Suddenly the music stops. The lights go down and the conductor walks out from behind the curtain and bows to the audience. Applause is deafening. The conductor raises his baton and the orchestra starts up again, playing the same piece of music as before. The audience is silent. The clown resumes his pose, unmoving, expressionless; the spotlight trained on his face. The music swells again and the conductor bows to an equally enthusiastic response from the audience. The conductor raises his baton, the orchestra plays the same piece of music. The audience is silent. The clown resumes his pose, unmoving, expressionless; the spotlight trained on his face. The music swells again and the conductor bows to a third equally enthusiastic response from the audience. The conductor raises his baton