I mentioned this in another comment thread, recently, but I value art, including music, for the fact that another human being(s) created it to express something. I have zero interest in it if it's AI-generated. The thought of endless content created from the void for me to gorge on like oreos fills me with nothing but despair.
A lot of music is not art. It's a content factory that uses humans.
Content factories that use AI will hopefully force humans to up their game.
Personally I feel humans are capable of so much more than pop music has become over the last 50 to 60 years.
A lot of today's music is so overproduced and formulaic.
I would love to see an arms race between humans and AI where humans are forced to continually adapt and get better.
The only thing about AI generated music that makes me sad is, I worry musical tastes will fragment even more and none of us will recognize the music our neighbors, classmates, or colleagues are listening to because we actively tailor our music to our personal tastes.
I use Suno and I've already noticed this.
A friend sends me a song they generated and I want to tweak it a bit to my personal preference. When we all can create music to our personal taste, we lose a little bit of the joy of all listening to the same song or album release.
I think AI will raise the bar for all kinds of artistic mediums. There’s already more music, literature, film etc than you can possibly consume - if you can easily make middling art with a prompt then it’s going to be swamped by all the other stuff, the really good, unique, fresh art will rise to the top. Perhaps they’ll use AI but it’ll still be the same amount of work put into and the quality will be better. I think nobody is going to get rich and famous from low-effort promoting.
With AI it’s very easy to create generic, common Pop or any other formulaic garbage music. It might be a good thing for the music industry, most of the low effort might just vanish in the sea of AI gen. This may actially raise the bar for music in general while at the same lowering the bar to simply prompting which is just a stage that will go away.
Survivorship bias. You can't tell at some point. You probably already are listening to AI songs, and looking at AI images. You can only tell what you know. Given the amount generated daily its more probable than improbable.
This is not a pro ai comment, I hope some bios bug bricks all the nvidia rtx gpus in the planet.
With that said... ai generated music, the same can be said about software... but compilers are basically ai, there is no way a for loop on extremely high level abstraction that then open connections to some service, generates jtokens, validates, and apply math non stop from a couple of lines is anything but alien to the 99% of us (yes I know you can write assembly for all your programs and you are better than the compiler)
What if you say, if humans where not involved and a phisically non electric instrument where involved and done with only humans, it's AI assited? because again you don't understand ALL the relationships, how it's designed every single thing, all the things in a music studio to master a song, ALL the related mechanisms used in the promotion, distribution and live execution of those songs... and yes, again there is some of you who can build all those things from sand and pumped from the ground with a tool you designed bare petroleum and program, design and execute EVERY SINGLE THING required to get a record of music you like...
So if a group of 20 people spends 20 weeks working with AI tools to get you a song, then you don't care I guess right?
Did you know that Enya for this song recorded thousand something times voices to make a chorus until it had a particular form... does that mixing of thousands of executions and the tools to analyze and give it the form wanted qualify as AI?
If you move sliders and push buttons and you don't understand the math behind it, are you vibe mixing a song?
Yes, if it is a "give me a catchy song with lyrics that talk about big butts" and then publish... yes this is crap.
This seems to be one of the few open-weight models that isn't just another "text to audio" generator. You can take existing sheet music, convert it to ABC notation, and then experiment with various covers.
I don't have a ton of time right now to really mess around with it, but I took 15 minutes to run it on my Mac M1 with an old melody I wrote back in high school for an RPG I was writing in VB6 (dating myself a bit here).
The model was trained on CC0, "royalty-free" music, so the outputs are going to sound a bit bland and generic. Model is not currently possible to finetune without the semantic tokenizer.
It's really depressing that I have gotten into music composition right when this is happening.
All of these projects are basically just destroying entire fields of human creativity.
It doesn't seem so bad at first when the quality is mediocre, but as soon as they get good, then any human composition will be completely devalued, despite the enormous amount of knowledge, skill and effort that goes into producing one.
A composer who writes a piece of music themselves, instead of being recognised and admired basically becomes the equivalent of someone who bakes their own sourdough instead of going to the supermarket: a curiosity, someone who does things the hard way for their own amusement.
Graphic artists and bloggers were the first to suffer this, but it feels like it's just going to happen to basically every type of creative expression that can be represented digitally. It's just a question of how many months until that happens.
I'm also saddened by the impact of tech on creative industries. But art always was something you do for yourself and to share with others, for some fundamentally human experience. Could an AI pray for you or ride your bike? I don't know anyone in my personal life who wants to listen to AI music, view AI art, or read AI books. I wish art careers were easier, but I don't think a career alone is the right reason to make art.
Much like the restaurant industry, creative industries will probably bifurcate. Cheap (AI, drivethrough, takeout) for daily and most use cases, experiential (vinyl records, concerts, upscale restaurants) for special occasions, connoisseurs.
Who cares? The world is being handed an infinite creation machine that conjures entire worlds into existence, radically reshaping the future of the species and what our descendants will be able to do, and your reply is ~"they took our jobs!"
Figure out how to stand on the shoulders of giants like any of your predecessors of note.
Have you observed the sheer monotony of this avalanche of AI-generated "creative" expression at all?
You have people pumping out an entire album in a few days simply because they can, repeatedly, and then they flood streaming services with their garbage. I forget which network it was but as of a few months ago, AI-generated submissions were at least half of all submissions.
You are free to perform create expression, I love writing blogs, my friends like reading and talking about the blogs with me, I dont care if Claude or GPT can write much better blogs. In the same way if it was just about creative expression, there would actually be 0 problems with AI-generated music, you would keep on making and listening to music you like, and you wouldn't care, but usually its not it, its people who want to make money, get famous, tie their value to the product that complain about this.
> you would keep on making and listening to music you like, and you wouldn't care
It becomes harder to find and therefore listen to music you like when every avenue of discovering music is drowned out with 1000 AI-generated songs for every 1 human-made song.
> people who want to make money,
Is it such a bad thing to want to be able to pursue your creativity full-time? For creative fields that require thousands of hours of practice to achieve results other people will enjoy, should we reserve such skilled expression only to those born wealthy enough to not need to work?
> It becomes harder to find and therefore listen to music you like when every avenue of discovering music is drowned out with 1000 AI-generated songs for every 1 human-made song.
Creative expression and consumption of media are different questions. You are right about that, but that's a separate issue.
> Is it such a bad thing to want to be able to pursue your creativity full-time? For creative fields that require thousands of hours of practice to achieve results other people will enjoy, should we reserve such skilled expression only to those born wealthy enough to not need to work?
Welcome to capitalism, enjoy your stay. And if you dont like it, you can always wait for the coming times when informational work is completely automated, which means that traditional social mobility completely disappears, and capital is locked/frozen forever and we will have serfdom instead. So I would recommend you enjoy the present.
Makes no sense - why would anyone use humans as serfs when AI is there. I think everyone will have AI and probably robotic automations, they will all be cheap and accessible.
We are still human and have human biases and desires, many humans can be good use to for example let rich people express power, experience sexual pleasures, and other emotions that are pre-wired in us. An AI cant be a good proxy for emotions, you cant whip a machine and know that it feels pain because of you. You cant pin a machine down and know that it can do nothing and has to feel powerless in your hands. You cant slice a machine open and know that it cannot do anything to you. All of this has already happened in the richest circles, you can imagine what happens when everyone has access to cheap robotic automatons, you think the richest people have been content with having what everyone has? Historically?
It's being handed an infinite slop machine, drowning out genuinely good content and making it harder than ever to discover. As it becomes harder to discover, fewer talented creatives are able to make a living. We are destroying our own culture with a machine that enforces regression to the mean on creativity.
Taste is still what separates AI output from human output regardless of whether it's music or software, IMO. Thinking in modes vs. functional harmony, how you hear a chord in context, which voicing you reach for etc. are things that can hardly be abstracted into strict music theory, let alone pattern-matched.
I imagine you can get pretty close to replicating an artist's sound if you specifically train on their output, but at that point it's the same question of whether you're satisfied with abstracting away the things that make writing music/software interesting to us (with music the answer's a lot more obvious since the point of writing music has always just been... to write music).
To add the fact that these AI models, readily help with soul draining music generation finetuning if you will ask it.
it will scrape youtube for audio, find ways to defeat provenance and all the other shenanigans but won't help a genuine cause because it wasn't intended
This is baffling to me. Idk what alignment means. Perhaps brainrot and endless mischaracterization of creativity is one of them
We are creating animated corpses out of our culture.
The point of art isn’t to generate beautiful patterns. It’s to create meaning. And you can’t have that without human care and intent.
Furthermore, that care needs to be intrinsically interwoven into the patterns that comprise the work. That’s what craft is. The mastery to generate exquisite patterns, and the care to infuse them with meaning at every level.
Without care, in a Heideggerian sense, we are left with something which tastes sweet but is completely hollow, perhaps even illusional.
Aren’t we all living with an illusion of intentionality of our actions, and the uncanniness of a machine is because it doesn’t pretend?
Meaning is listener’s own perception (author’s own intent is a suggestion at best - if I’d be paid a dollar every time I thought some artist meant something when they didn’t or meant something different, I’d sure have a good wad of cash), and when a listener learns about the purely mechanistic “authorship” they start to feel uncanny unless they find an outing in appreciating the mechanicity itself.
For an informed take (from a professional musician, composer, and arranger) on where this is going for musicians and the music industry, I really recommend Adam Neely's video essay "Suno, AI Music, and the Bad Future": https://www.youtube.com/watch?v=U8dcFhF0Dlk
I've been waiting for symbolic music generators for ages. This is so nice for musicians. Being able to intelligently translate parts, generate additional parts, generate sheet music from audio, generate variations on pieces, making pieces easier or harder.
I wish folks spend more time on agentic music genertion instead of a single black box prompt to music.
Similar to coding, where you are have a bunch of tools that can do the drudge work for you (the mundane things in mixing mastering for example), but still retain full creative freedom and expression.
I am not articulating this well, but basically transitioning from IDE->Coding harnesses what is the DAW-> ??
The vocals in the few songs I listened to are so very clearly AI. I find Suno's much more credible in many genres.
If anyone has tried Suno's Studio 2, I would love to hear your take on it. At $24-30/month, it's approaching Ableton Live 12 Suite rent-to-own territory, without the "own" part.
I say this as someone with no skin in the game, but I don’t think it’s necessary for AI to replace human creativity in music. Instead, it can be a tool for augmentation.
There has almost always been backlash against new technologies in music. Ultimately, musicians adopted those technologies and continued producing great works.
I recently dug some 20-year-old CDs out from storage that were full of riffs and chord progressions for songs I never got around to completing. I fed them to Suno as a sort of “what might these have sounded like if I’d finished them?” experiment. I found the results quite impressive and plan to publish them some time in the near future.
None of the tracks sound like marketable products to me, and I certainly don't think AI is going to generate the next Bohemian Rhapsody -- but it definitely could be a great thing for curing writer's block.
That example "Comedy" sounds like the most soulless synthetic example of "music" ever. Like the music analogue of a PR-speak article of a big corpo generated by an LLM. It's still technically impressive but it's 0/10, absolutely empty of soul.
All AI generated art feels somewhat masturbatory to me, but AI generated music is the most baffling of them all. It's like what if someone thought Muzak had too much soul.
It's interesting that the “Classical Music” sample ended up with a style prompt of “Contemporary Christian”.
It's even more interesting that the “Contemporary Christian” music it generated was specifically Mormon music (specifically about the exile of Lehi and his family from Jerusalem into the wilderness, during which they reach the ocean, build a boat, and sail to the Americas), but in the style of contemporary Christian rock.
The majority of people, I think, don't want to listen to AI music or view AI art. Systems like this will produce muzak for ubers, cafes, phone queues, advertisements. Some artists will make hyperreal work by sampling it. But to listen to these "songs" willingly is not something I expect most people will choose to do.
I really want to like ai music but none of them seem to be trained on reward models that reward "ambiance" or any sort of interesting sound design (which this paper obviously doesn't even concern), which might be reflective of the people training them not having niche music tastes
all of these fall very flat, many of them sound like generic commercial tunes at their worst. there is obviously melody and structure but none of it sounds good.
"The Petty and the Small;
Are overcome with gall ;
When Genius, having faltered, fails to fall.
Klapaucius too, I ween,
Will turn the deepest green
To hear such flawless verse from Trurl's machine."
You know how they used heavy metal music to break the spirit of Manuel Noriega? I'm sure there's some DoD (or is it DoW now?) psychological operations people right now studying the prolonged effects of high volume mediocre AI slop music.
The playlist included "the sound of jet planes all night" and "the screams of rabbits being slaughtered". I don't think they really need AI for that, anything loud would probably do the trick after 51 days.
The use case is control. It's essentially a controlnet for the actual music writing. So a musician could compose melody, harmony, and lyrics and generate many performances of the same song until they get one they like. A non-musician could similarly generate the symbolic input from scratch, and perhaps they like the composition but not the performance. This allows them to re-render and re-render until they like the performance.
> a musician could compose melody, harmony, and lyrics and generate many performances of the same song until they get one they like
Can't relate to this. Art doesn't come out as a left-brained problem solving exercise or identifying the right product for a market. It's about expression. You do it when you're feeling things.
I'm a composer and I can 100% get behind this workflow. I will often compose on one instrument (guitar or keys) and then throw the midi into a DAW and experiment with sounds.
I'm not species-ist. If a digital sentient being has something to say and they can express it through music, I'm more than willing to listen.
But listening to these samples, it's obvious that, while technically proficient, they have no voice. Funnily enough, neither does most of the human produced music slop that existed before gen AI.
All it exposes is that most people have no taste. This is as good as shuffling through popular songs on Spotify.
Am I as good as Claudio PRC, Donato Dozzy, Ken Ishii or Takkyu Ishino? Not even close. But wanting to make more is reward enough for me to keep trying.
Content factories that use AI will hopefully force humans to up their game.
Personally I feel humans are capable of so much more than pop music has become over the last 50 to 60 years.
A lot of today's music is so overproduced and formulaic.
I would love to see an arms race between humans and AI where humans are forced to continually adapt and get better.
The only thing about AI generated music that makes me sad is, I worry musical tastes will fragment even more and none of us will recognize the music our neighbors, classmates, or colleagues are listening to because we actively tailor our music to our personal tastes.
I use Suno and I've already noticed this.
A friend sends me a song they generated and I want to tweak it a bit to my personal preference. When we all can create music to our personal taste, we lose a little bit of the joy of all listening to the same song or album release.
With that said... ai generated music, the same can be said about software... but compilers are basically ai, there is no way a for loop on extremely high level abstraction that then open connections to some service, generates jtokens, validates, and apply math non stop from a couple of lines is anything but alien to the 99% of us (yes I know you can write assembly for all your programs and you are better than the compiler)
What if you say, if humans where not involved and a phisically non electric instrument where involved and done with only humans, it's AI assited? because again you don't understand ALL the relationships, how it's designed every single thing, all the things in a music studio to master a song, ALL the related mechanisms used in the promotion, distribution and live execution of those songs... and yes, again there is some of you who can build all those things from sand and pumped from the ground with a tool you designed bare petroleum and program, design and execute EVERY SINGLE THING required to get a record of music you like...
So if a group of 20 people spends 20 weeks working with AI tools to get you a song, then you don't care I guess right?
Did you know that Enya for this song recorded thousand something times voices to make a chorus until it had a particular form... does that mixing of thousands of executions and the tools to analyze and give it the form wanted qualify as AI?
If you move sliders and push buttons and you don't understand the math behind it, are you vibe mixing a song?
Yes, if it is a "give me a catchy song with lyrics that talk about big butts" and then publish... yes this is crap.
I don't have a ton of time right now to really mess around with it, but I took 15 minutes to run it on my Mac M1 with an old melody I wrote back in high school for an RPG I was writing in VB6 (dating myself a bit here).
If anyone wants to hear what it sounds like:
https://mordenstar.com/other/yue2-tests
All of these projects are basically just destroying entire fields of human creativity.
It doesn't seem so bad at first when the quality is mediocre, but as soon as they get good, then any human composition will be completely devalued, despite the enormous amount of knowledge, skill and effort that goes into producing one.
A composer who writes a piece of music themselves, instead of being recognised and admired basically becomes the equivalent of someone who bakes their own sourdough instead of going to the supermarket: a curiosity, someone who does things the hard way for their own amusement.
Graphic artists and bloggers were the first to suffer this, but it feels like it's just going to happen to basically every type of creative expression that can be represented digitally. It's just a question of how many months until that happens.
Figure out how to stand on the shoulders of giants like any of your predecessors of note.
You have people pumping out an entire album in a few days simply because they can, repeatedly, and then they flood streaming services with their garbage. I forget which network it was but as of a few months ago, AI-generated submissions were at least half of all submissions.
It becomes harder to find and therefore listen to music you like when every avenue of discovering music is drowned out with 1000 AI-generated songs for every 1 human-made song.
> people who want to make money,
Is it such a bad thing to want to be able to pursue your creativity full-time? For creative fields that require thousands of hours of practice to achieve results other people will enjoy, should we reserve such skilled expression only to those born wealthy enough to not need to work?
Creative expression and consumption of media are different questions. You are right about that, but that's a separate issue.
> Is it such a bad thing to want to be able to pursue your creativity full-time? For creative fields that require thousands of hours of practice to achieve results other people will enjoy, should we reserve such skilled expression only to those born wealthy enough to not need to work?
Welcome to capitalism, enjoy your stay. And if you dont like it, you can always wait for the coming times when informational work is completely automated, which means that traditional social mobility completely disappears, and capital is locked/frozen forever and we will have serfdom instead. So I would recommend you enjoy the present.
Makes no sense - why would anyone use humans as serfs when AI is there. I think everyone will have AI and probably robotic automations, they will all be cheap and accessible.
I imagine you can get pretty close to replicating an artist's sound if you specifically train on their output, but at that point it's the same question of whether you're satisfied with abstracting away the things that make writing music/software interesting to us (with music the answer's a lot more obvious since the point of writing music has always just been... to write music).
This is baffling to me. Idk what alignment means. Perhaps brainrot and endless mischaracterization of creativity is one of them
The point of art isn’t to generate beautiful patterns. It’s to create meaning. And you can’t have that without human care and intent.
Furthermore, that care needs to be intrinsically interwoven into the patterns that comprise the work. That’s what craft is. The mastery to generate exquisite patterns, and the care to infuse them with meaning at every level.
Without care, in a Heideggerian sense, we are left with something which tastes sweet but is completely hollow, perhaps even illusional.
Meaning is listener’s own perception (author’s own intent is a suggestion at best - if I’d be paid a dollar every time I thought some artist meant something when they didn’t or meant something different, I’d sure have a good wad of cash), and when a listener learns about the purely mechanistic “authorship” they start to feel uncanny unless they find an outing in appreciating the mechanicity itself.
So many possibilities.
Similar to coding, where you are have a bunch of tools that can do the drudge work for you (the mundane things in mixing mastering for example), but still retain full creative freedom and expression.
I am not articulating this well, but basically transitioning from IDE->Coding harnesses what is the DAW-> ??
If anyone has tried Suno's Studio 2, I would love to hear your take on it. At $24-30/month, it's approaching Ableton Live 12 Suite rent-to-own territory, without the "own" part.
There has almost always been backlash against new technologies in music. Ultimately, musicians adopted those technologies and continued producing great works.
I recently dug some 20-year-old CDs out from storage that were full of riffs and chord progressions for songs I never got around to completing. I fed them to Suno as a sort of “what might these have sounded like if I’d finished them?” experiment. I found the results quite impressive and plan to publish them some time in the near future.
None of the tracks sound like marketable products to me, and I certainly don't think AI is going to generate the next Bohemian Rhapsody -- but it definitely could be a great thing for curing writer's block.
It's even more interesting that the “Contemporary Christian” music it generated was specifically Mormon music (specifically about the exile of Lehi and his family from Jerusalem into the wilderness, during which they reach the ocean, build a boat, and sail to the Americas), but in the style of contemporary Christian rock.
Previously: https://news.ycombinator.com/item?id=46641627
https://electricliterature.com/wp-content/uploads/2017/11/Tr...
"The Petty and the Small; Are overcome with gall ; When Genius, having faltered, fails to fall. Klapaucius too, I ween, Will turn the deepest green To hear such flawless verse from Trurl's machine."
https://www.bbc.com/news/world-latin-america-40090809
Or I suppose they could just put "baby shark" on a loop.
The playlist included "the sound of jet planes all night" and "the screams of rabbits being slaughtered". I don't think they really need AI for that, anything loud would probably do the trick after 51 days.
Can't relate to this. Art doesn't come out as a left-brained problem solving exercise or identifying the right product for a market. It's about expression. You do it when you're feeling things.
This is that.
are you kidding
It would be useful to be able to generate backing vocals/hums/melismas and whatnot, that could be plugged into a DAW.
But listening to these samples, it's obvious that, while technically proficient, they have no voice. Funnily enough, neither does most of the human produced music slop that existed before gen AI.
All it exposes is that most people have no taste. This is as good as shuffling through popular songs on Spotify.
Mainstream is for suckers.
Properly mixed ofc.
https://www.discogs.com/artist/9699799-Neurojacker
Am I as good as Claudio PRC, Donato Dozzy, Ken Ishii or Takkyu Ishino? Not even close. But wanting to make more is reward enough for me to keep trying.