How Artificial Intelligence Helped Make an Experimental Pop Album

YACHT’s “Chain Tripping,” made using only A.I.-generated melodies and lyrics, is the subject of a new documentary

Singer Claire L. Evans of the band YACHT performs onstage during "GIORGIO'S LIVE" in 2018 in Los Angeles, California.
Singer Claire L. Evans of YACHT performs in Los Angeles. Scott Dudelson / Getty Images

When you listen to experimental pop band YACHT’s discography, the 2019 ​​album Chain Tripping fits right in. Pulsing with glitchy synth sounds, infectious bass riffs and the sweet voice of lead singer Claire L. Evans, Chain Tripping is a successful, Grammy-nominated album that sounds like YACHT, through and through. It’s such a success, you might never know it was generated by artificial intelligence.

But it was: Every riff, melody and lyric on Chain Tripping was developed by A.I. systems—even the album’s title. 

That strange, tedious process—at times frustrating and at times awe-inspiring—is now the subject of The Computer Accent, a new documentary from directors Sebastian Pardo and Riel Roch-Decter that is “heartening or horrifying depending on your viewpoint,” according to the film’s own synopsis.

To make Chain Tripping, the members of YACHT transformed their entire back catalog into MIDI data. (MIDI, which stands for musical instrument digital interface, allows electronic instruments and computers to communicate.) They then fed that data, piece by piece, to machine learning models—primarily Google’s MusicVAE, which helps artists “create palettes for blending and exploring musical scores.” YACHT followed the same process with songs by their musical inspirations and peers, and fed the lyrics of their songs into a lyric-generating model to come up with words.

Though A.I. generated the building blocks—melodies, riffs, beats and lyrics—the members of YACHT (which, fittingly, is an acronym for Young Americans Challenging High Technology) still had to manipulate them into complete songs.

“It wasn’t something where we fed something into a model, hit print and had songs,” Evans told Ars Technica’s Nathan Mattise in 2019. “We’d have to be involved. There’d have to be a human involved at every step of the process to ultimately make music … The larger structure, lyrics, the relationship between lyrics and structure—all of these other things are beyond the technology’s capacity, which is good.”

Evans and her bandmates, Jona Bechtolt and Rob Kieswetter, hand-selected their favorite A.I. generations and then arranged them into the songs that make up Chain Tripping. They set rules for themselves: “We can’t add anything. We can’t improvise anything. We can’t harmonize,” Bechtolt told KCRW’s Madeleine Brand in 2019. “We decided it would be just a subtractive process. So we could remove things, like we could take out a word, but we couldn’t add a word for the lyrics. Same with the drum patterns and the melodies.”

While The Computer Accent, which is currently touring at select theaters around the world, is about A.I. technology, it is mostly concerned with the humans behind the technology.

“A theme that emerged in the film is A.I. is a mirror,” Pardo tells the Moveable Fest’s Stephen Saito. “Not only is it trained on everything we’ve made and who we are and what we value, you also see in it what we recognize as useful, so it is a symbiote. To ignore the humans that are engaging with it would be to not tell the complete story, so that’s where we really started to say it’s a two-hander: that technology is human and needs to include the human perspective and work for humans.”

Once you know to look for them, traces of A.I. can be found throughout Chain Tripping. The evidence is primarily in its lyrics, which at times veer into the absurd and uncanny. “Your teeth are all an ocean,” Evans sings on “Stick it to the Station.” “I’m so in love I can feel it in my car,” begins “Loud Light,” which also features the lyric “I want your phone to my brain.”

That slight uncanniness is part of Chain Tripping’s charm, Evans told Ars Technica. “This tech is evolving so quickly,” she said. As that evolution progresses, “a lot of the stuff we appreciated for its wonkiness and strangeness will be so polished. They’ll produce melodies and lyrics that are unrecognizable as machine generated. They’ll be perfect.”

“Something will be really lost,” she continued, “because when it’s not perfect there’s this specialness unique to our moment in time.”

Get the latest stories in your inbox every weekday.