2 min read

1010Benja made a Suno song that actually works

The Verge says 1010Benja’s “Semiramis' Dream” stands out from typical Suno output by combining human performance with heavy iterative editing.

Image: The Verge

Generative AI music rarely escapes the charge that it sounds flat and disposable. But The Verge argues that 1010Benja’s “Semiramis' Dream” is a notable exception — a Suno-assisted track that is actually compelling.

The song opens Time Has Nothing To Do With What You Choose…, 1010Benja’s latest EP, and the publication describes it as infectious, driven by a jungle beat and anchored by Benja’s unmistakably human vocals. Unlike many AI-generated songs, it reportedly avoids the usual tells. Even the most obviously synthetic element — a choir of backup vocalists — is partly obscured by hyperpop-influenced rapid-fire chops and the heavily processed vocal style common in contemporary pop.

Benja has been direct about how the track was made. In an interview with Hearing Things, he said:

“My friend Patrick Holder did the beat. I recorded the vocals. Then we fed Suno the elements, settled on something, brought it out, edited it on Ableton, and then put it back into Suno. So when you look in Deezer, it marks the song as AI-generated. We’re not hiding it. We don’t feel any shame about it.”

1010Benja

According to The Verge, that workflow is what sets the track apart from the bulk of Suno output. Benja wrote the lyrics, sang the vocals, collaborated on the performed elements, then repeatedly pushed the material through Suno and Ableton. He estimated that he went through this loop a few hundred times for “Semiramis' Dream.”

Recommended reading

Moonshot AI halts Kimi K3 signups after demand spike

He also does not pretend the tool is ethically neutral. The article notes that Benja acknowledges the environmental damage tied to generative AI, while taking a bleak view of whether artists can reverse the broader shift.

At the same time, The Verge argues there is little in the song that could not have been created without AI. The publication suggests the choir effect, for example, might have been replicated with layered performances and vocal processing. Still, for a musician who has struggled financially and endured periods of homelessness despite praise such as Pitchfork’s Best New Music for Ten Total, the appeal of cheaper tools is obvious.

The result does not convert the article’s author into an AI-music believer. It does, however, make a narrower point: in skilled hands, Suno does not have to produce pure slop.

Ava Chen

AI Editor

Ava covers the rapidly evolving world of artificial intelligence, from foundational models and research labs to the real-world economics of intelligence. With a background in computational linguistics, she cuts through the hype to find out what actually works. She firmly believes that benchmarks are just marketing until reproduced in the wild.

via The Verge

// Keep reading