Luke Dzwonczyk is an M.A./Ph.D. student in music at UC Berkeley, where he works closely with the Center for New Music and Audio Technologies (CNMAT). Recently, he built interactive instruments for the Berkeley Dance Project, created a generative soundtrack for a film installation, and published papers on computer-assisted orchestration. His research interests include computational creativity, audio generation with neural networks, and sound visualization.

Bass baritone Nicholas Isherwood is one of the leading singers of early music and contemporary music in the world today. He has sung in many of Europe's leading festivals and opera houses. Isherwood has worked closely with composers such as Sylvano Bussotti, Elliott Carter, George Crumb. Hans Werner Henze, Mauricio Kagel, György Kurtág, Olivier Messiaen, Giacinto Scelsi, Iannis Xenakis, among many others. He has improvised with Steve Lacy, Joelle Léandre, David Moss and Sainkho Namtchilak. Isherwood collaborated with Karlheinz Stockhausen for 23 years, singing numerous world premieres, including Montag, Dienstag, and Freitag from Licht.

This piece was not written by me. I did not write the text. I did not write the music. I did not set the text to the music. The text was written by GPT-J and the music and setting of the text were generated by a Markov chain chained on Gregorian chant.

This work is an exploration of questions of machine creativity. Can computers be creative? How do we value art differently based on whether it was made by a human or a machine? What is happening when a program creates a piece of music? Ultimately, we have a historical re-reading of chant music through the lens of modern technology: neural networks, Markov chains, and artificial intelligence.