Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Suno v4.5

suno.com

Post reply on HN
Print view View original

151–160 of 291 posts

Re: Suno v4.5

#151

Post by tern »

bongodongobob wrote: post #100
tern wrote: post #97

The fact that LLMs compute an average of human culture is more apparent in music AIs than any other medium. You cannot get these things to do anything original, same as with images, designs and creative writing—and it's not an "intelligence" problem. I'm not sure if this is solvable, but I think it should be a bigger research topic. If anyone knows of any papers on this, I haven't found one yet (not sure what to sear…

Any musician will tell you most music isn't original. You just don't have the ear for it. You telling me Green Day's songs are all unique and original? Even jazz uses 6-2-5-1's over and over. Unless you only listen to avante garde prog rock or something, all of music is derivative. And that's ok. Every song being a unique snowflake isn't important. If you like it or it makes you feel something, that's all that matter…

Green Day (was) definitely original. The level of unoriginality I'm talking about goes way beyond "pop music is the same old chords from the 50s" or "the 70s were the golden age and everything since then is derivative."

What's the basis for this? Unfortunately it's hard to describe, but I've listened to a wide variety of popular and niche genres my whole life with a specific eye toward appreciating all the different ways people appreciate music and I know when something feels new.

Even most (or all?) pop music feels new. If it wasn't, I don't think it would be popular. Sure, it's all derivative, but what makes music enjoyable is when it combines influences in a fresh way.

"French house polka" achieved by doing a statistical blend of the two genres just isn't that interesting—it misses so many ways that things are combined by artists—specific details of the texture of the sound, how it's recorded, cultural references, tons of tiny little influences from specific artists and other genres, etc.

I've tried very specific prompts in Suno and it's not even close to useful for someone who knows what they're doing. The image generators are hardly better—things overwhelmingly trend toward a fixed set of specific styles that are well-represented in the training sets.

This critique falls down in certain areas though. Using tools like Suno to come up with songwriting ideas can be fantastic—as long as you have the taste to curate the outputs and feed it into your own creative process. It's also fantastic for creating vocal samples, and I'm sure it'll crush it for functional music (advertisements, certain types of social media) in short order

Re: Suno v4.5

#152

Post by vunderba »

killerstorm wrote: post #145

I'd be a lot more interested in AI which can take existing music as the base. I don't want a new song, I want to hear music I love in a new way. Like img2img but track2track.

Have you actually looked at Suno? Img2Img is effectively "Cover mode" - you upload an existing WAV/MP3.

Re: Suno v4.5

#153

Post by bongodongobob »

Velorivox wrote: post #125
bongodongobob wrote: post #100

Earlier quoted context omitted.

Any musician will tell you most music isn't original. You just don't have the ear for it. You telling me Green Day's songs are all unique and original? Even jazz uses 6-2-5-1's over and over. Unless you only listen to avante garde prog rock or something, all of music is derivative. And that's ok. Every song being a unique snowflake isn't important. If you like it or it makes you feel something, that's all that matter…

All books are derivative too, the English ones use the same 26 characters over and over.

You're intentionally missing the point, but ok.

Re: Suno v4.5

#155

Post by __loam »

tern wrote: post #97

The fact that LLMs compute an average of human culture is more apparent in music AIs than any other medium. You cannot get these things to do anything original, same as with images, designs and creative writing—and it's not an "intelligence" problem. I'm not sure if this is solvable, but I think it should be a bigger research topic. If anyone knows of any papers on this, I haven't found one yet (not sure what to sear…

I think we should stop research into automating creative labor and study something that actually benefits people.

Re: Suno v4.5

#156

Post by __loam »

ronsor wrote: post #25
progbits wrote: post #17

Aren't they still in active lawsuit with Sony etc about training on music without license? Yet still releasing new products? I guess they are hoping for the Uber outcome where they earn enough money during the illegal phase so they can pay some tiny fine and keep going.

Illegal? If the record companies were so obviously going to win, they could've obtained a preliminary injunction to stop Suno's business. They didn't, so the service continues.

Pretty sure napster also continued to operate during ongoing legal actions but I am not a lawyer

Re: Suno v4.5

#157

Post by __loam »

93po wrote: post #104
randyrand wrote: post #92

Earlier quoted context omitted.

I think it's more straightforward to argue it's transformative fair use.

fair use requires it be non-profit which doesnt work for suno

Fair use has consideration for whether the derivative work disrupts the market for the original, it doesn't mean you can't use it for profit as we saw with the Google books case.

Re: Suno v4.5

#158

Post by __loam »

randyrand wrote: post #92
pier25 wrote: post #31

Earlier quoted context omitted.

AFAIK the lawsuit is still ongoing. Suno admitted to train their models with copyrighted music and are now defending the position that music copyrights and royalties are bad for the future of music.

I think it's more straightforward to argue it's transformative fair use.

Transformative is one of 4 conditions that the court uses to decide if something is fair use. This question is still in active litigation in the courts.

Re: Suno v4.5

#159

Post by corlinp »

kelseyfrog wrote: post #91

The real potential of tools like Suno isn’t in cranking out radio-ready hits. It’s in creating music that doesn't have commercial incentives to exist. Case in point: Functional Music. I started using it to generate songs that reinforce emotional regulation strategies -things like grounding, breathwork, staying present. Not instructional tracks, which would be unbearable, but actual songs with lyrics that reflect actu…

I used Suno to generate rap versions of Feynman's first lecture. It turned out really well!

https://suno.com/playlist/d2886382-bcb9-4d6d-8d7a-78625adcbe...

Re: Suno v4.5

#160

Post by energy123 »

tern wrote: post #97

The fact that LLMs compute an average of human culture is more apparent in music AIs than any other medium. You cannot get these things to do anything original, same as with images, designs and creative writing—and it's not an "intelligence" problem. I'm not sure if this is solvable, but I think it should be a bigger research topic. If anyone knows of any papers on this, I haven't found one yet (not sure what to sear…

I think the problem is the lack of a verifier to check the attempt at creativity in a tight loop. Creativity could just be randomness (off the existing average) plus selection done many times over a 30 year career.

That is, you try something new (random) and you, the human, are also the verifier to see whether that random new thing was subjectively good, and then you select based on that.

In this understanding of creativity, creating a new style is a gradual process of evolution (mutation and selection) where your own brain is a necessary part of carrying out the selection. "Did the new idea (mutation) I just tried make me feel good or not (selection)?"

That activity of you being the verifier is effortless and instant, but the AI fundamentally can't tap into the verification and so it has no ability to do the selection step after randomness, and so it is impossible for creativity to emerge no matter the architecture (unless you somehow create a proxy for a human verifier which seems insanely hard).

The only solution I can see to this is to try to simulate this process, seems possible but hard.

Post reply on HN