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

AI-generated sad girl with piano performs the text of the MIT License

suno.com

Post reply on HN
Print view View original

351–360 of 389 posts

Re: AI-generated sad girl with piano performs the text of the MIT License

#351

Post by navane »

memsom wrote: post #287
navane wrote: post #178

These songs don't have any hooks. Melodies don't get repeated. They all just meander along. I think as they get better at making these great middle of the road songs, edgy music will reemerge. Whatever AI will be good at, will immediately devalue, in the realm of arts. Just how photography gave way to non-realistic art and how drum machines made sloppy drums (or ridiculous apex twins) hip. Then, the artifacts we see…

This is your comment as a song: https://suno.com/song/c974b1ca-c69e-47a9-994c-9172fae52927

Thank you!

Re: AI-generated sad girl with piano performs the text of the MIT License

#352

Post by ryandrake »

xcv123 wrote: post #321
arrowsmith wrote: post #299

Earlier quoted context omitted.

You must live under the world's largest rock if you don't think that there's a commercial audience for corny, generic, cringeworthy and shitty music.

I am under a rock of denial of how bad popular music has become. I was checking out some other tracks on this site and now believe AI could eventually take a lot of musicians jobs, for advertising and so on. But there won't be an AI Kurt Cobain.

AI's bread and butter will be "customers who just want generic art for generic commercial use, any quality art, and pay as little as possible for it." It's probably never going to need to create the next Billie Jean hit.

Re: AI-generated sad girl with piano performs the text of the MIT License

#354

Post by ragazzina »

fps_doug wrote: post #217
navane wrote: post #178

These songs don't have any hooks. Melodies don't get repeated. They all just meander along. I think as they get better at making these great middle of the road songs, edgy music will reemerge. Whatever AI will be good at, will immediately devalue, in the realm of arts. Just how photography gave way to non-realistic art and how drum machines made sloppy drums (or ridiculous apex twins) hip. Then, the artifacts we see…

> These songs don't have any hooks. Melodies don't get repeated. They all just meander along. I've been playing around with it for a few days now. While I agree that it seems impossible to create songs with a more "sophisticated structure" (for lack of a better word off the top of my head), you still can get better results by fine-tuning, as is always the case. If you just request "rock music" or "jazz", you get very…

>it seems impossible to create songs with a more "sophisticated structure"

Is it my impression, or if you just put:

    [verse]
    ..
    ..

    [chorus]
    ..
    ..
it works mostly OK?

Re: AI-generated sad girl with piano performs the text of the MIT License

#355

Post by mjgoeke »

navane wrote: post #178

These songs don't have any hooks. Melodies don't get repeated. They all just meander along. I think as they get better at making these great middle of the road songs, edgy music will reemerge. Whatever AI will be good at, will immediately devalue, in the realm of arts. Just how photography gave way to non-realistic art and how drum machines made sloppy drums (or ridiculous apex twins) hip. Then, the artifacts we see…

We're already there! Impose some structure in the textual representation of the song and it'll respect the structure musically:

example - "I only ate 3 cheeseburgers"

https://suno.com/song/c15f0251-fbac-4a30-a3e1-002dbc78cb79/

edit: yes, I agree this example amusingly reinforces the rest of what parent is saying

Re: AI-generated sad girl with piano performs the text of the MIT License

#356

Post by stusmall »

mjgoeke wrote: post #355
navane wrote: post #178

These songs don't have any hooks. Melodies don't get repeated. They all just meander along. I think as they get better at making these great middle of the road songs, edgy music will reemerge. Whatever AI will be good at, will immediately devalue, in the realm of arts. Just how photography gave way to non-realistic art and how drum machines made sloppy drums (or ridiculous apex twins) hip. Then, the artifacts we see…

We're already there! Impose some structure in the textual representation of the song and it'll respect the structure musically: example - "I only ate 3 cheeseburgers" https://suno.com/song/c15f0251-fbac-4a30-a3e1-002dbc78cb79/ edit: yes, I agree this example amusingly reinforces the rest of what parent is saying

I know it isn't the point you are trying to make, but I can't think of a better way to re-enforce OP's point of "mediocrity will be even more available" than a mid-00s style, pop country song about eating hamburgers. "Toby Keith but with less to say" might be the gold standard of mediocrity.

Re: AI-generated sad girl with piano performs the text of the MIT License

#357

Post by gwern »

fennecfoxy wrote: post #336
latentsea wrote: post #301

Earlier quoted context omitted.

You can make them have a hook if you structure it right. The default prompt on Suno winds up as "verse, verse 2, chorus" for the structure, which indeed does sort of sound like a song, but not a song at the same time. When I changed things around and put a chorus in twice I wound up getting an actual song with a hook. I assume the 2 minute limit has a lot to do with this. Often I find Suno generates anywhere between…

Yeah I have noticed that Suno's lyric generation is very canned sometimes, but also for timing - it oftens generates 3-4 (longish) lines for a verse where for the music there should be 2-3.

That's the ChatGPT style. It is extremely stereotypical when it comes to writing lyrics or poetry: 4 lines, rhyming, with metronome regularity. Both Suno & Udio seem to use ChatGPT for lyrics, and it's a terrible choice, which should be ripped out in favor of Claude or anything else. (Basically, any LLM which can pass the "write a non-rhyming poem" test prompt would be a better choice.)

Re: AI-generated sad girl with piano performs the text of the MIT License

#358

Post by ta8645 »

mgaunard wrote: post #319
ta8645 wrote: post #50

Earlier quoted context omitted.

Humans aren't perfect. It's what gives us our unique little quirks. Same as AI at this stage of its growth. It won't make such silly little mistakes tomorrow.

That's the whole problem of inference: it's just wrong outside of the trivial cases. Humans are not limited to inference-based reasoning.

Some humans aren't even up to the standard of inference-based reasoning; it's quite a spectrum. But there's little reason to believe that carbon based reasoning, is fundamentally superior to silicon based reasoning, in the long term.

Re: AI-generated sad girl with piano performs the text of the MIT License

#359

Post by rendall »

acureau wrote: post #340
rendall wrote: post #231

Earlier quoted context omitted.

> I'm not sure I follow your argument, because neither synthesizers nor recordings write music. The argument is that each technology advance accompanied resistance followed by adaptation. "Recorded music" was arguably as paradigmatically disruptive over "live music" as "AI generated music" will be.

The two are fundamentally incomparable beyond the surface level fact that "things will be different". Recorded music changed the way we experience music. AI tools may change the way we make music. From my perspective the implications of this are dire. AI can completely remove the human element. The skill, creativity, and collaboration required to produce music is a big part of my appreciation for it. Once that's gone…

> The two are fundamentally incomparable

You're not wrong. A paradigm shift is not an incremental change but a disruption of fundamentals.

> From my perspective the implications of this are dire.

These changes are scary, especially as people try to come to practical terms with the new reality.

> AI can completely remove the human element. The skill, creativity, and collaboration required to produce music is a big part of my appreciation for it.

I still hate autotune. I feel that it ruined music. But, on the other hand, it allowed people who were excellent musicians but terrible singers to make excellent music, even masterpieces. I don't think autotune was a paradigm shift really, but it was pretty disruptive.

People are deeply creative, social, collaborative, musical, artistic, hierarchical and status conscious. These traits will always drive people to make music and share it, and derive meaning from it. People will still pay other people for the music they make.

Photography utterly disrupted the social role that painters held as documentors. No one needed to hire a good painter to have a portrait. They could hire a photographer more cheaply for more accurate documentation. Artists working in the medium of painting really had to grapple with the question of what art is, if academic faithful representation of reality is no longer valued by society. Painting thus began to change. Impressionism led to Suprematism, Dadaism, Surrealism, Abstract Expressionism, Conceptualism, Modernism, Post Modernism.

Artists today will have to grapple with similar questions raised by AI generated art. But humans are creative, indomitable, curious and tenacious. I am absolutely excited to see the art that future human artists will make in the face of all of this.

Re: AI-generated sad girl with piano performs the text of the MIT License

#360

Post by skydhash »

criddell wrote: post #199
TeMPOraL wrote: post #158

Earlier quoted context omitted.

Hard disagree. I don't think anyone considers that, unless they're an art critic, a philosopher, or a snob. For a normal person, whether something is art or not, is a mix of 1) whether they like it, 2) whether they can, or conceivably could, enjoy it together with other people, and 3) whether they're supposed to enjoy it or call it art, because other people claim they do (social proof). Examples: - Pop songs are stro…

I never thought much of Van Gogh’s work until my sister recommended I read Irving Stone’s novel Lust for Life . I loved it and did a deeper dive on Van Gogh and his contemporaries. Now, he’s one of my favorite artists. For me, one problem with AI art is that there isn’t context for any of it. It’s just there and didn’t come from anywhere. Eventually, some prompt engineer may build up a coherent body of work that is m…

I like listening to Soundtracks, but if you've not played the game/watched the movie, it can be hard to get into it (Listening to NieR: Automata is a journey). Listening to one track is like reading one chapter of a book. It may be your favorite one, but there's something more substantial into consuming the whole work. I know people listen to music to set up moods, but everyone has that playlist/album where they listen to the whole thing just for the sake of listening. Or watch a painting for contemplation, not to judge whether it's beautiful or perfectly made. And that is why I can't enjoy AI generations. There is nothing to connect too.

P.S. I don't mind people using AI as tools, but the human agency needs to be visible and relatable. If it's only a prompt, don't ask why I don't value it.

Post reply on HN