SUNO is killer!

Explore how Machine Learning and AI can expand musical creativity while keeping the human in the creative workflow. This forum is dedicated to respectful dialogue where diverse perspectives are welcomed.
Post Reply New Topic
RELATED
PRODUCTS

Post

I am not the same, I am now certified 20% robot, minimum. It might be more. Brought to you by Carl's Junior.

Post

Innermost wrote: Tue Jul 14, 2026 9:19 pm Like what? He is not the same?
Hell no!!!

Once renowned for having such exacting standards when it came to filter topologies, he claimed he’d walk off the dance floor if he heard a poor filter sweep. Now we’re supposed to believe the same ghettosynth is listening to lowest common denominator lo-fi hip hop slop.

These ARE NOT the same people!!

Post

ghettosynth wrote: Tue Jul 14, 2026 10:08 pm I am not the same, I am now certified 20% robot, minimum. It might be more. Brought to you by Carl's Junior.
ghettoGPT
Paradoxical developer of obsidian neural - Because paradox is the only things which leads to unity.

Post

el-bo (formerly ebow) wrote: Tue Jul 14, 2026 10:14 pm
Innermost wrote: Tue Jul 14, 2026 9:19 pm Like what? He is not the same?
Hell no!!!

Once renowned for having such exacting standards when it came to filter topologies, he claimed he’d walk off the dance floor if he heard a poor filter sweep. Now we’re supposed to believe the same ghettosynth is listening to lowest common denominator lo-fi hip hop slop.

These ARE NOT the same people!!
I think that you are mixing incompatible contexts. I very much care about the sound quality when I'm on the dance floor. The music is loud, often played through unforgiving horn tweeters, and some of the artifacts of things that bug me explicitly are amplified there. At the same time, that is not the state of affairs when I'm trying to get work done and have music playing that sits just below the level of conscious awareness.

For the former, I want to feel every beat and I want the characteristic cream of a filter matched to the application. For the latter I just don't want the tracks to disturb me. Just enough interest so that I don't turn it off, but not so much that it causes me to engage the music for more than a split second or two at a time.

Years ago I worked at home for a year and this was long before streaming. So, to easily listen to music all day the radio was the only real choice. So, I chose the local public radio station that played jazz. The thing is, at that time, I didn't really recognize a lot of the standards by name. By the end of the year though, I did, and they became distracting. I don't want to know the artists or the songs, and I don't want to memorize them over time while I'm working. I think that this is the kind of thing that AI is going to foster at low cost.

As far as underground music, I'm not convinced that any of the models are trained on enough to do a good job TBH. They do ok at the harder styles, but they lack the subtlety for the kind of house/techno that interest me. Current research identifies this as a problem. It requires the model to represent a persistent source plus explicit, temporally varying control states. Systems such as JASCO introduce fine-grained temporal conditioning precisely because global text descriptions are too blunt for this sort of control. Related, it's just too much to infer about the underlying model about the characteristics of the filter sweep. So, they tend to sound tame and boring. Not distorted, per se, just not interesting.

So, no, I am not convinced by SUNO 90s house, it's largely terrible and either comes out chill, or way too modern sounding. Now, where it matters much less is in muted mostly convincing acoustic sounds, e.g., LoFi hip hop, for when I'm studying. It works reasonably well for those and adjacent genres.

Post

el-bo (formerly ebow) wrote: Tue Jul 14, 2026 10:14 pm Once renowned for having such exacting standards when it came to filter topologies, he claimed he’d walk off the dance floor if he heard a poor filter sweep.
When I think of all the good people we lost to them storming off the dancefloor in protest to RBJ cookbook filters

Image

Post

gearwatcher wrote: Wed Jul 15, 2026 11:30 am
el-bo (formerly ebow) wrote: Tue Jul 14, 2026 10:14 pm Once renowned for having such exacting standards when it came to filter topologies, he claimed he’d walk off the dance floor if he heard a poor filter sweep.
When I think of all the good people we lost to them storming off the dancefloor in protest to RBJ cookbook filters
Right! Someone has to have some standards up in here. But, less of a protest, more like a suspension of the suspension of disbelief. It's a bit like two shoes in a dryer, you can't really recover from it so you go do something else.

Post

So epic, OMG, I'm peaking, I'm being taken to a whole new level!!!


Post

suno was hacked revealing all the things scraped to make it.

https://www.404media.co/hack-reveals-su ... nd-genius/
The AI music generation tool Suno scraped millions of songs and lyrics from YouTube Music, Deezer, and Genius, as well as from the stock music libraries Pond5, Jamendo, Freesound, the International Music Score Library Project, and podcasts via RSS feeds, according to a hacker who breached the company and shared data about Suno’s training libraries with 404 Media. The hacker was also able to access user information for hundreds of thousands of Suno’s customers, as well as Stripe payment information, they said.
The hacked data is a rare look at exactly how AI models and tools are built. Suno is one of the largest AI music generation tools on the internet, and has been the subject of several major lawsuits from the record industry, which accused the company of training on millions of copyrighted songs. As part of these legal proceedings, Suno previously admitted that it was trained on “essentially all music files of reasonable quality that are accessible on the open internet,” which included a total of “tens of millions of recordings.” Suno has been making the argument that it is allowed to train on copyrighted works as fair use in those cases, one of which has been settled.

Post

So they stole tons of intellectual property just like other AI companies. I'm extremely shocked :o
dayjob wrote: Wed Jul 15, 2026 4:26 pm suno was hacked revealing all the things scraped to make it.

https://www.404media.co/hack-reveals-su ... nd-genius/

Post

I can't believe Suno stole my song. Bastards.

Post

Fascist thieves.
REAPER + Davinci Resolve Pro on Manjaro KDE. Neve 88m. Focusrite 18i20 2nd gen. Neumann NDH30 headphones. Mics: Telefunken TF39, AT4050, Miktek C7e, EV RE-15. VSTs: u-he Hive 2, F'em, Renoise Redux, Apisonic Speedrum 2.

Post

Of course it’s obvious news but nice to have more details and receipts. Also, the relatively weak security of these systems is worth thinking about. The people making these things aren’t so smart.
0degree wrote: Wed Jul 15, 2026 5:10 pm So they stole tons of intellectual property just like other AI companies. I'm extremely shocked :o
dayjob wrote: Wed Jul 15, 2026 4:26 pm suno was hacked revealing all the things scraped to make it.

https://www.404media.co/hack-reveals-su ... nd-genius/

Post

Are any of you putting bot blockers on your websites or is Google crawling still too important?

Examples would be when cloudflare checks if you are human or what linuxmusicians.com uses.
REAPER + Davinci Resolve Pro on Manjaro KDE. Neve 88m. Focusrite 18i20 2nd gen. Neumann NDH30 headphones. Mics: Telefunken TF39, AT4050, Miktek C7e, EV RE-15. VSTs: u-he Hive 2, F'em, Renoise Redux, Apisonic Speedrum 2.

Post

People are complaining about the quaility Suno outputs nowadays, and this must have reason. They have stolen music too!
Mac Mini M4 Pro | 14 Cores (10P/4E) | 48GB RAM | Studio One | Reason | Bitwig Studio | Logic Pro | FL Studio | Cubase Pro | Waveform | Reaper | Renoise | ~1000 VSTs/AUs | ~350 REs

Post

dayjob wrote: Wed Jul 15, 2026 5:37 pm Of course it’s obvious news but nice to have more details and receipts. Also, the relatively weak security of these systems is worth thinking about. The people making these things aren’t so smart.
Actually there's a very intelligent process at work. Suno was designed to fail. After all A.I. can design a DAW in a few days. No big deal. The whole point is to sway people towards A.I. knowing the hostility that will have to be dealt with. So you create a "Suno" predetermined to be popular and fail like A Milli Vanilli.
Alternatives will come up promising better security and better performance options and voila, you win the faith of the sheep. It's actually not rocket science it's the way things have been working since the dawn of apes.
After Milli Vanilli, look at all those bands and artists who were dismissed as ever going the lip - syncing/instrument - syncing route.

Post Reply

Return to “Machine Learning and AI for Music Creation”