It's going to be interesting to see how that plays out when you can make just about any kind of media you wish. (Especially when you can mix this as a form of 'embodiment' to realize relationships with virtual agents operated by LLMs.)
It's going to be interesting to see how that plays out when you can make just about any kind of media you wish. (Especially when you can mix this as a form of 'embodiment' to realize relationships with virtual agents operated by LLMs.)
Not to sound too crass, but a parallel could be drawn to smelling one's own farts and wondering why no one else appreciates the smell.
Music is one of the worse examples to pick for claiming that people don't regurgitate in art. Everything in music builds off one another, and a lot of music (especially music that's seen as lower quality) is described as being just collections of cliches. The reason why "sad music" sounds sad isn't because there's something about instrument choices, key, chords, melody, tempo etc that is measurably intrinsically "sad" - it's because these are stereotypes that the creator has combined together to invoke a certain association in the listeners. If you were extra cynical, you could describe the entire musical field as people largely conditioning themselves over generations to like certain qualities of sound and hate others.
And that applies to almost all art. Basically everything people make is based on stuff that came before that - and it's frustrating to encounter hubris that assumes there's some magical creative process going on inside human brains that will never ever be even approximated by any other means.
Maybe we will, maybe we won't. In the same way maybe we will be able to create life artificially, maybe not. The AI I am critiquing today is what Tamagotchi is to human life. Sure, you can get attached to it and think it's expressing real emotions and wonder why other people are being "hubris" by not realizing how wonderful it is.
Yes, it is. You should try it.
Welcome to making music lol. Since there is so much of it, you have to make the absolute best to even be considered. And then, because so many people make the absolute best, people only care about the persona making the music (as great as you are, you aren’t Taylor Swift, Kendrick Lamar, Damon Albarn). Your friends will never care about your music just because you are friends, don’t fall into that trap. Also nobody cares about music without good lyrics, because again, there is just so much instrumental content out there that sounds the same, lyrics differentiate it with a human, emotional element.
Just make stuff for fun. Listen to it every now and then and feel the magic of “hehe I made that”
Well, that's an exaggeration if I've ever seen one. Firstly, so much of current chart music has atrocious lyrics. And secondly, instrumental music is very popular.
With all due respect, how could there be when at the click of a button you can generate entire songs? You didn't come up with the chord progression, the structure, the melodic motifs, or the lyrics.
My attachment to my works is directly proportional to the amount of effort it took to create them.
It's not the craft that drives attachment in this case but the emotional resonance of something that you think should exist finally existing.
Author's attachment is to a large degree based on the false notion that they somehow contributed to the creation process.
The generic, frigid, un-interesting "product" that is produced by said AI is why no one other than the prompter is moved by the result.
I can agree that:
> "a sad rock song about a breakup"
Is probably not going to capture or express your ideas or emotions because you haven’t given it enough. In contrast, writing the lyrics or giving the model a ton more context can absolutely produce something that captures and expresses your ideas and emotions.
At the end of the day I don’t make music for the masses (hell, I’ve only generated a handful of final songs that I’ve liked) but the people I have made them for (or the ones just for me) have enjoyed them quite a bit.
I’m not a songwriter nor am I a musician and I never will be. That’s not where my skills lie and it’s not a skillset I want to learn and hone. AI/LLM tools give me the ability to express myself in a medium that previously was effectively impossible and it makes people I care about smile and that’s good enough for me.
> can absolutely produce something that captures and expresses your ideas and emotions
The right analogy here is to imagine an infinite museum where you can wander until you find a piece that expresses your emotions. It has nothing to do with the act of your expression, and everything to do with you resonating with a piece produced by someone/something else.
> At the end of the day I don’t make music for the masses
Fair. But you also don't "make music" for yourself. At most you write lyrics.
My point wasn’t to debate the merit of generated music, it was simply to highlight the effect I described.
Production requires specifying very precise requirements, which the current gen AI is unable to follow. Even at the most fuzzy production level like "a song with strings and a choir", Suno will generate something completely irrelevant. And if you will try to go deeper -- use a classic Moog synth line in the chorus -- don't expect to generate something meaningful.
I won't argue that in the most broad sense, prompt engineering is a creative process. Picking which shoes to wear to work is also a creative process. My argument is that this has barely anything to do with the process of music composition or production. You can literally reuse the same prompt to generate an image or a poem.
It’s not a sense of pride or accomplishment. I don’t know what it is. Maybe a small amount of pride. It’s hard to say. But there is a definite connection that feels different listening to songs i requested vs those that other people have.
Both Suno and Udio allow paid subscribers to upload their own clips to extend from. It works for setting up a beat or extending a full composition from a DAW.
Suno's is more basic than Udio's which allows in painting and can create intros as well as extensions, but the tools are becoming more and more powerful for existing musicians. With Udio you can remix the uploaded clip so you can create the cord progression and melody using one set of instruments or styles (or hum it) and transform it into another.
I also use this feature all the time to move compositions from one service to the other. Suno is better at generating intros and interesting melodies while Udio is better at the editing afterwards.
yeah its not surprising that you wouldn't volunteer this, man
What did you hope to prove? That I'm right? That songs that I feel a connection to sound terrible to you? An astute reader with some basic emotional intelligence would notice that is the entire point of my comment. Not that 'mouthbreathers on the Internet don't appreciate my art', but that things I 'create' by typing stuff in on a keyboard still manifests this odd connection that is just going to be enhanced as these capabilities increase.
Those songs were something a friend of mine asked for, not the ones I was talking about. Don't worry, I've protected the internet from my poor musical taste.