AI Research
An indie band is blowing up on Spotify, but people think it’s AI
An indie psych rock band has amassed more than 850,000 listeners on Spotify in a matter of weeks and generated buzz throughout the music industry — but nobody is exactly sure if it’s real or not.
The Velvet Sundown, a band bent on “Saving Modern Rock,” according to its Instagram account, has even some music industry veterans confused. The images put forward by the band all look like they were created by artificial intelligence. The music? That’s harder to say.
Rick Beato, a music producer with more than 5 million subscribers on YouTube, identified what he called “artifacts,” particularly in one of the tracks’ guitar and keyboard parts. He said that can indicate a song was created by AI.
“This is having a lot of problems, and I suspect that it may be because this is an AI track,” Beato said in a YouTube video, after running one of The Velvet Sundown’s songs through Apple’s Logic Pro track splitter. “Every time you have an AI song, they are full of artifacts.”
Whether the band is real, fake or something in between, its emergence and the broader debate about it add to a growing concern about the future of art, culture and authenticity in the era of advanced generative artificial intelligence. Many major tech platforms have already seen floods of AI-generated content, while AI influencers are becoming increasingly common on social media platforms.
Velvet Sundown appears to have first emerged in June, according to its social media profiles. On Spotify, the band has a “Verified Artist” badge, offering some sense of authority. On X, The Velvet Sundown teased an upcoming album, “Paper Sun Rebellion,” and nodded to questions about doubts about the band’s origins.
Aside from the quick rollout of songs, its uncannily plasticine promotional images of band members have prompted accusations of AI use as well.
In a video announcing the release of its upcoming album later this month, the band pushed back against accusations that it isn’t “real,” stating in one video that “you believed the lie, and danced to it anyway.”
“They said we’re not real,” the account posted. “Maybe you aren’t either.”
The band’s bio on Spotify claims that the group is composed of four people: singer Gabe Farrow, guitarist Lennie West, Milo Rains, “who crafts the band’s textured synth sounds,” and percussionist Orion “Rio” Del Mar. Farrow purportedly also plays the mellotron, which is an electro-mechanical instrument that plays recorded sounds when its keys are pressed.
“There’s something quietly spellbinding about The Velvet Sundown,” their Spotify bio states. “You don’t just listen to them, you drift into them. Their music doesn’t shout for your attention; it seeps in slowly, like a scent that suddenly takes you back somewhere you didn’t expect.”
Questions about the band’s origins were further complicated after other social accounts purporting to represent the band began rejecting claims that it was using AI-generated images or music, as well as a person who spoke to Rolling Stone claiming to be connected to the band who called it an “art hoax.” That person later admitted in a Substack post that his claim to represent the band was itself a hoax.
The Velvet Sundown said that the person quoted in the article is not affiliated with it in “any way.”
“He does not represent us, speak for us, or have any connection to this project,” The Velvet Sundown said in a statement to NBC News via Instagram.
On Thursday, the social media accounts tied to the band’s Spotify account posted that “someone is trying to hijack the identity of The Velvet Sundown by releasing unauthorized interviews, publishing unrelated photos, and creating fake profiles claiming to represent us.”
The Velvet Sundown’s YouTube publisher, Distrokid, did not respond to requests for comment. Spotify also did not respond to a request for comment.
The band’s meteoric rise highlights modern issues around AI and how difficult it can be to verify what is and is not real on the internet. Last year, Google researchers found that AI image misinformation has surged on the internet since 2023. A Consumer Reports investigation found that leading AI voice-cloning programs have no meaningful barriers to stop people from nonconsensually impersonating others.
According to the music streaming app Deezer, which uses its own tool to identify AI-generated content, 100% of The Velvet Sundown’s tracks were created using AI. Deezer labels that content on its site, ensuring that AI-generated music does not appear on its recommended playlists and that royalties are maximized for human artists.
“AI-generated music and AI bands may generate some value to the user, so we still want to display that,” Alexis Lanternier, the CEO of Deezer, said. “We just want to make sure that the remuneration is taken in a different way.”
Every week, about 18% of the tracks being uploaded to Deezer — roughly 180,000 songs — are flagged by the platform’s tool as being AI-generated. That number has grown threefold in the past two years, Lanternier said.
Suno and Udio, both generative AI music creation programs, declined to say whether The Velvet Sundown’s music was created using their software.
“I think people are getting too far down the rabbit hole of dissecting is it AI, is it not AI? And forgetting the important question, which is like, how did it make you feel? How many people liked it?” said Mikey Shulman, CEO and co-founder of Suno.
According to Suno’s rights and ownership policy, songs made by its users who are subscribed to its higher-tier plans are covered by a commercial use license. That allows them to monetize and distribute songs on platforms like Spotify without attributing them to Suno.
“There are Grammy winners who use Suno, you know, every day in their production,” said Shulman.
Recently, Grammy Award-winning record producer Timbaland launched an AI artist named TaTa with his new entertainment company, Stage Zero. He told Billboard that TaTa, who created a catalog of AI-generated music through Suno, was neither an “avatar” nor a “character.”
Suno was one of two AI companies sued last year by major record labels — including Universal Music Group, Sony Music Entertainment and Warner Music Group — which allege that the companies infringed on the labels’ recording copyrights in order to train their music-generating models.
About a year into the legal battle, however, the music labels have begun talks to work out a licensing deal so that Suno and Udio could use copyrighted recordings by compensating the artists for their work, according to a Bloomberg report published last month.
It’s a trend that’s become worrisome to artists like Kristian Heironimus, who is a member of the band Velvet Meadow (not to be confused with the now-viral The Velvet Sundown).
“I’ve been working for, like, six years just constantly releasing music, working my day job,” Heironimus said. “It is kind of disheartening just seeing an AI band, and then — in, like, what, two weeks? — [have] like, 500,000 monthly listeners.”
The creep of generative AI into music and other creative industries has incited backlash from those who worry about the devaluation of their human work, as many AI developers have been known to scrape data from the internet without human creators’ knowledge or consent.
Beyond ethical debates about the consequences of the AI impact on human labor, some online worry about the rise of low-quality AI slop as these tools grow increasingly capable of replicating voices, generating full-length songs and creating visuals from text prompts.
Heironimus said there are similarities between his band, Velvet Meadow, and The Velvet Sundown, beyond the names. One of the members pictured in The Velvet Sundown’s Spotify band photo, for example, looks similar to a photo of Heironimus when he used to have long hair, he said. The bands also fall within the same genre, though Heironimus described The Velvet Sundown’s tracks as “soulless.”
Shulman, of Suno, said most streaming music is already “algorithmically driven.”
“People don’t realize just how depersonalized music has become and how little connection the average person has with the artist behind the music,” he said. “It’s a failure of imagination to think that in the future, it can’t be a lot better.”
But Lanternier, of Deezer, argues that as AI continues to evolve, streaming platforms should also be trying to ensure artists can make enough royalties to survive.
“People are not only interested in the sound. They are interested in the whole story of an artist — in the whole brand of an artist,” Lanternier said. “We believe that what is right to do is to support the real artist, so that they continue to create music that people love.”
AI Research
Agentic AI Accelerates Shift From ‘Sick’ Care
AI Research
Microsoft announces public preview of deep research in Azure AI foundry
Synopsis
This tool aims to accelerate research and deployment of frontier AI technologies, further strengthening Microsoft’s position in enterprise-grade generative AI solutions.
Elevate your knowledge and leadership skills at a cost cheaper than your daily tea.
Subscribe Now
AI Research
Deep Research And More From New AI Models
Young vocalist with a microphone singing on stage
Did you hate these annoying songs? Check out what new deep research AI tools can do.
It’s all well and good to tell people to get on ChatGPT, or Claude, or Gemini, and get their hands dirty using an AI model – but some people want more detail. They want to know how to use the best new tools in a more granular way.
Deep research is one of the newest and most impressive functions of today’s large language models. But most people haven’t heard of it yet, let alone used it.
Ethan Mollick is someone I associate with the vanguard of AI research. With former MIT connections, Mollick represents a leading voice in this field. So I was reading his latest blog post about different models, and how to use them.
Mollick breaks down the most useful models for Claud, ChatGPT and Google in the following categories: “chat,” “work” and “hard problems.”
Claude, he notes, is generally better for privacy, where you need to select for this in ChatGPT, and may compromise some functionality with Google.
Then Mollick embarks on a description of deep research capabilities that are baked into some of the newest models, but not yet available for free. This is so new that it’s still paywalled and rationed for paying users.
The Promise of Deep Research Functionality
Deep research is available from OpenAI, and from Google, and from Anthropic, too.
When you look at the unveiling of the research function, you see a lot of reports around February.
So how do you access this kind of result?
I found a recent post about this from the “OpenAI cookbook” in June, where the poster talks about downloading a Python SDK, and API work.
It turns out, though, that you can select “deep research” in the prompt section of ChatGPT 4.5, if you are a paying Plus or Pro user, and get your deep research report that way.
Asking for Deep Research from ChatGPT 4.5
I wanted to try this for myself, so based on what I was experiencing in the moment, I centered on compiling a report of the most annoying songs from 1990 through 2025.
My query: “please create a report on the most annoying music from 1990 until 2025, segmented annually.”
Simple, right?
First, ChatGPT asked me to clarify a few basic questions:
“To create a detailed report on the ‘most annoying music’ from 1990 to 2025, could you please clarify a few things:
- What do you mean by ‘annoying’? Are you referring to songs widely criticized, overplayed, polarizing, or based on listener polls or memes?
- Should the list be global or focus on a specific region (e.g., U.S., UK, etc.)?
- Do you want one song per year, or multiple per year if applicable?
- Would you like the report to include explanations or cultural context for each selection?”
And I answered:
“1. all of the above 2. US-based 3. multiple songs per year 4. Yes.”
“Thanks!” GPT responded. “I’ll compile a U.S.-focused report covering the most widely criticized, overplayed, or culturally mocked songs from 1990 to 2025. This will include multiple songs per year, along with context explaining why they were considered annoying—drawing from music critics, listener polls, memes, radio overplay complaints, and public opinion.”
Then the report started. Indeed, it took more than 10 minutes to compile, with CoT displays like “searching ‘Rico Suave’: worst song’ and ‘looking for Macarena.’
Check Out GPT’s Chain of Thought
Actually, here are some of the interesting CoT notes the system provided while doing research on dozens of sites (it spent a lot of time reading the Guardian!)
I’m mapping out recent headlines and thought pieces, like those from Global News and the Guardian, all noting “Baby Shark” as the most annoying song. Hm, that’s interesting.
I’m preparing the list of most annoying songs from 1993-1995, considering “What’s Up,” “Cotton Eye Joe,” “Macarena,” and “Wonderwall.” However, I’m thinking through the inclusion of other notable tracks like “Rico Suave” for earlier years.
(There’s that ‘Rico Suave’ song again.)
I’m mapping out the hits and misses of 2001-2006, with 2005’s viral sensations like “Crazy Frog” and “Photograph” by Nickelback taking center stage. Hm, that’s interesting—these tracks seem to evoke strong reactions.
(Note how the model is actually ‘taking notes’ while researching, giving us little bits of personality along with the actual meat of the report.)
Here’s a funny comparison:
I’m comparing the impact of Nickelback’s “Rockstar” in 2006 to Soulja Boy’s “Crank That” in 2007. The former was widely criticized, while the latter was loved by many, raising questions about musical taste over time.
A research-based note:
I’m digging through songs by genre and year, considering widespread opinion and specific examples to select the most frequently labeled annoying tracks.
I’m evaluating hits like Meghan Trainor’s “All About That Bass” (2014) and Tyga’s “Stimulated” (2015) for their ubiquity and frequency of being labeled annoying. Progressing through last five years gradually.
I’m digging through songs by genre and year, considering widespread opinion and specific examples to select the most frequently labeled annoying tracks.
I’m evaluating hits like Meghan Trainor’s “All About That Bass” (2014) and Tyga’s “Stimulated” (2015) for their ubiquity and frequency of being labeled annoying. Progressing through last five years gradually.
And then there was this:
“Noticing the challenge of time limitations, I’m figuring out how to balance inclusion of pivotal examples against the need for conciseness.”
So the model is actually trying to triage its work. This is next-level stuff.
Finally, GPT appeared to wrap up, dotting its I’s and crossing its Ts:
“I’m checking to see if the ‘Achy Breaky’ song contains any references to anthropomorphic sharks.”
Eventually, I got the full report. It ranges dozens of pages, and provides great coverage of over a quarter century of horrible, terrible music. A few standouts, with years:
1990
- “Ice Ice Baby” – Vanilla Ice (1990): This hip-hop crossover hit became a pop culture punchline due to its cheesy lyrics and ubiquitous play. While it was initially a chart-topping success, critics later lambasted it; Spinner magazine ranked it the second-worst song in history, and Blender ranked it fifthen.wikipedia.org. A Houston Press critic even dubbed it the worst song ever by a Texas artist, claiming it “set back the cause of white people in hip-hop by a decade”en.wikipedia.org. Its overexposure turned the once-popular anthem into an annoyance for many listenerscraftyourhappyplace.com.
- “Rico Suave” – Gerardo (1990): A bilingual novelty rap track that peaked in 1991, “Rico Suave” was a one-hit wonder often cited on “worst song” lists. Its goofy, exaggerated Latin lover persona and repetitive chorus wore thin quickly. Blender magazine’s infamous list of the “50 Worst Songs Ever” placed “Rico Suave” among its ranks (in the high 30s), and retrospective pop culture forums frequently hold it up as an example of early ’90s pop cringeculturecrossfire.comforums.thefashionspot.com. The song’s catchphrase chorus (and its shirtless music video) made it memorable, but also widely mocked in the years since.
1994
- “Cotton Eye Joe” – Rednex (1994): This techno-hoedown remix of an old folk tune became a staple at sports games and parties – much to many people’s annoyance. With its frenetic fiddle loops and the grating “If it hadn’t been for Cotton Eye Joe” chorus, the track wears thin fast. CBS News put it at #1 on a “Worst Songs from Jock Jams” list, calling it an “unholy hybrid of country-fried fiddle kitsch and relentless hi-NRG drums”en.wikipedia.org. A Toronto Star critic dubbed it the worst song of the ’90s, describing it as “straight drivel”en.wikipedia.org. Even wrestler-turned-rocker Chris Jericho said it’s one of his least favorite songs ever – naming it alongside “Mambo No. 5” on his personal worst listen.wikipedia.org. Despite its party ubiquity, few ever actually wanted an “EDM-hillbilly” mashup like thisen.wikipedia.org.
1997
- “Barbie Girl” – Aqua (1997): This novelty dance-pop hit was simultaneously a global chart-topper and a critical punching bag. Its bouncy, plastic sound and exaggerated vocals (“Come on Barbie, let’s go party!”) made it a staple of late-’90s radio and kids’ parties, but also an irritant to many. Rolling Stone readers voted it the worst song of the ’90sen.wikipedia.org, and NME put it atop their worst-single list as wellen.wikipedia.org. While Aqua intended it as satire, the song was widely mocked; it even sparked a lawsuit from Mattel for tarnishing the Barbie brand. Decades later, it remains a guilty pleasure earworm that routinely tops “most annoying” song listscraftyourhappyplace.com.
Fast-forward a bit:
2013
- “The Fox (What Does the Fox Say?)” – Ylvis (2013): An absurdist novelty song by a Norwegian comedy duo, “The Fox” unexpectedly became a global viral hit in late 2013. Its EDM-lite beat and litany of animal sounds (ring-ding-ding, wa-pa-pa-pow!) made it the “Macarena” of the YouTube era – funny at first, then torturous on repeat. Kids loved the silliness, while parents and many others quickly tired of it. The song was essentially one long joke about animal noises, and once the joke wore off, what remained was an insanely repetitive chorus of nonsense. Rolling Stone readers later voted it one of the most annoying songs of the 2010s, and USA Today called it “the year’s most aggravating meme song.” Like other meme hits, it got played at school events and even on radio as a curiosity, amplifying the annoyance for those who never wanted to hear “Hatee-hatee-hatee-ho!” again. Ylvis intended it as a parody of EDM pop – ironically achieving exactly the kind of ubiquitous earworm they were spoofing, to the annoyance of millions.
- “Baby Shark” (global viral hit – charted 2018/2019): {See 2016 above.} In 2018, “Baby Shark” finally chomped its way onto international music charts (hitting the US Top 40 by early 2019)theguardian.comtheguardian.com. This was the year the song truly went pandemic, crossing from kids’ YouTube into mainstream consciousness. By the fall of 2018, articles were calling it “the year’s most annoying song” outrighttheguardian.com. Parents everywhere pleaded for mercy from the doo-doo-doos. The Guardian wryly noted how even people who hadn’t heard it knew of it through cultural osmosis – often via tales of toddlers playing it on endless repeat, driving their families madtheguardian.com. Once it hit the radio and dance remixes appeared, there was no escape. “Baby Shark” in 2018 exemplified how a simple children’s ditty could unite millions in shared, head-throbbing frustration. (Fun fact: that year a viral social post joked that the Geneva Convention should classify repeated “Baby Shark” play as a form of torture – a sentiment many a worn-out babysitter would second.)globalnews.catheguardian.com
2023
- “Peaches” – Jack Black (Bowser) (2023): Featured in The Super Mario Bros. Movie, this over-the-top piano ballad sung by Jack Black (in character as Bowser) became a TikTok smash and even entered the Billboard Hot 100. It’s intentionally comedic – Bowser professing love for Princess Peach with a dramatic “Peaches, Peaches, Peaches” chorus. Kids and gamers found it hilarious and catchy; others quickly found it grating (especially if they hadn’t seen the movie context). The chorus is essentially one word (peaches) repeated incessantly with operatic bombast. Within weeks, clips of people annoyed by their friends or children endlessly singing “Peaches” popped up online. Though short, the song’s earworm power is strong. One AV Club article quipped that it’s the kind of novelty song “destined to annoy parents everywhere while their offspring replay it 1,000 times.” It’s a fresh example of how a song can go viral and charm its way into your brain – and then, thanks to sheer overuse, make you never want to hear the word “peach” again (sorry, Georgia).
Some Thoughts on Voice Mode
Let’s move back to the blog post: after delving into the above stuff, Mollick also covers the verbal capabilities of new systems that really change the interface. As he notes, you can talk to these models while you’re in the car, or on a walk, or anywhere that you have the space and time.
I think verbal communication is going to finally make LLM responses “real” to us. And that’s all I have to say about that – for now.
I think all of this is deeply informing to people who want to be practical about LLM use. The deep research function in particular is something people will be learning about as time goes on. How many of us will figure it out before something new comes along that makes it obsolete?
In any case, this was an excellent guide to how to make the most of AI in today’s environment.
-
Funding & Business7 days ago
Kayak and Expedia race to build AI travel agents that turn social posts into itineraries
-
Jobs & Careers7 days ago
Mumbai-based Perplexity Alternative Has 60k+ Users Without Funding
-
Mergers & Acquisitions7 days ago
Donald Trump suggests US government review subsidies to Elon Musk’s companies
-
Funding & Business6 days ago
Rethinking Venture Capital’s Talent Pipeline
-
Jobs & Careers6 days ago
Why Agentic AI Isn’t Pure Hype (And What Skeptics Aren’t Seeing Yet)
-
Funding & Business4 days ago
Sakana AI’s TreeQuest: Deploy multi-model teams that outperform individual LLMs by 30%
-
Jobs & Careers6 days ago
Astrophel Aerospace Raises ₹6.84 Crore to Build Reusable Launch Vehicle
-
Funding & Business7 days ago
From chatbots to collaborators: How AI agents are reshaping enterprise work
-
Jobs & Careers4 days ago
Ilya Sutskever Takes Over as CEO of Safe Superintelligence After Daniel Gross’s Exit
-
Funding & Business4 days ago
Dust hits $6M ARR helping enterprises build AI agents that actually do stuff instead of just talking