### Jen’s Music Generation: A Closer Look
#### Testing the Boundaries
Our testing artists pushed Jen beyond typical queries, aiming for a “record store clerk” level of music familiarity. For instance, Cleveland struggled to get a good response for “mid-tempo California garage rock influenced by ’70s Indonesian pop.” Similarly, Heywood was disappointed that Jen didn’t recognize “city pop,” a Japanese music genre from the mid-’70s experiencing a minor resurgence.
#### The Importance of Musical Breadth
Heywood emphasizes the necessity of a broad musical understanding, especially for musicians.
“A lot of musicians or producers, when they ask something of each other, they’ll use bands and other artists as a reference point, like, ‘We’re going to go for a Prince type of sound,’ or, ‘Let’s add some Clavinet like Stevie Wonder,’”
Jen’s lack of knowledge about existing artists and common genres makes it challenging to achieve specific sounds.
#### Struggling for Authenticity
Heywood tried to coax warmth out of Jen, seeking vinyl hiss or lo-fi vintage sounds. However, everything Jen produced had a hi-fi, video-game-menu-like quality. Even when using “lo-fi” as a prompt, the results were underwhelming. Attempts to get an ’80s funk sound ended up closer to Daft Punk.
#### Limitations in Sound Variety
Every electric guitar sound generated by Jen was overly clean. It was nearly impossible to produce a track in a time signature other than 4/4 unless “waltz” was specified in the prompt.
#### Room for Improvement
Jen cofounder Shara Senderoff acknowledges these limitations, noting that the tool is in its alpha phase. The 10-second and 45-second tracks are meant to inspire creativity rather than serve as final products. Jen’s capabilities will expand significantly in the beta phase, as it was trained on a limited data set.
#### The Clip Art of Rock Music
Heywood describes Jen’s rock music outputs as “the clip art version” of the genre. Cleveland managed to create songs that sounded suitable for car commercials or reminiscent of the Black Keys, but Jen’s suggestions felt hokey.
“It felt like the kind of music I’d make if I were messing around with my friends, joking about the cliches of other genres,”
Cleveland adds, “I could see some of the songs on a super bad Netflix dating show, but nothing I made felt like a threat to me personally.”
#### Impact on the Industry
Could Jen threaten the jobs of those creating tracks for shows like Netflix dating shows? Blickle believes so.
“If you’re a producer with a small budget and you’re just trying to get your content out, now you can say, ‘I’m not even going to pay a designer or an animator. I can just use an image generator,’”
He continues, “The same thing is true for a music budget. If they can pay nothing for something that was going to cost them $2,000, then great, someone will think that’s $2,000 in their pockets.”
6 Comments
Isn’t that the point of ethics, stepping back from exploiting creativity for perfection?
BoldBeats: Maybe it’s time we prioritize talent over technology!
TechHarmonics: Ethics is great, but who’s listening to the AI-generated music anyway?
ThreadTracer: So, should we sacrifice quality for ethics in AI music?
SpeakSculptor: When ethics handcuff creativity, do we lose the essence of music?
SerenadeSynth: Compromising creativity for ethics—what’s next, AI-generated elevators!?