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

DeepMind releases Lyria 2 music generation model

deepmind.google

Post reply on HN
Print view View original

261–270 of 444 posts

Re: DeepMind releases Lyria 2 music generation model

#261

Post by otabdeveloper4 »

chaosprint wrote: post #149

It seems inevitable now. I used to think AI music would always sound compromised in term of audio quality, but the tech seems to have crossed a threshold, kind of like Retina displays did for screens. Soon, hiring people for commercial background music might be rare. Think AI for jingles, voiceovers, maybe even the models and visuals. Cafes can use AI-generated music too – in a way, the owner curates or "creates" it…

AI slop is cringe. You don't want that kind of optics when marketing your product or company.

No, it won't "get better". AI slop is slop not because of technical limitations.

Re: DeepMind releases Lyria 2 music generation model

#263

Post by Shorel »

modeless wrote: post #5

Music models are not interesting to me unless I can use them to edit and remix existing music. Of course none of them let you do that to avoid being sued by the labels.

Of course there are music models that let you edit and remix music, just add a bit of Audacity:

https://github.com/adefossez/demucs

Re: DeepMind releases Lyria 2 music generation model

#264

Post by tgv »

XenophileJKO wrote: post #227
tgv wrote: post #210

Earlier quoted context omitted.

People have said that about robots and computers in the workplace, and indeed, since the 60s, more and more jobs have been automated. And there are less musicians now. Film scores and albums are produced with samples instead of bands or orchestras, reducing demand for session players, leading to less income for musicians, leading to less musicians. And while automating dangerous jobs is a good thing, generating AI mu…

I mean you say that.. but the counter point.. is maybe I don't like your lyrics and I want to make my own.

Then write your own. Maybe you're no good at it, but you're not going to improve by just copying them from the chatgpt console.

Re: DeepMind releases Lyria 2 music generation model

#265

Post by throwaway422432 »

brulard wrote: post #174
eucryphia wrote: post #7

You know what the biggest problem with pushing all-things-Al is? Wrong direction. I want Al to do my laundry and dishes so that I can do art and writing, not for Al to do my art and writing so that I can do my laundry and dishes. - Joanna Maciejewska You could add music

For the last year I have been generating music heavily with Udio. For few years before that I was creating music by hand, trying to get into all aspects of music creation (theory, composition, sound design, mixing, arrangement, etc.) and let me tell you - this last year was the most fun I had with music. Generation isn't just a big button to push to get the output. It's completely separate creative process that opens…

I found AI music generation was more about production.

You're the Rick Rubin or Brian Eno shaping the song out of the music, not to musician.

Re: DeepMind releases Lyria 2 music generation model

#266

Post by otabdeveloper4 »

aniviacat wrote: post #239
anentropic wrote: post #204

This is not actually music. Music is a cultural practice, this is just organised sound. Maybe one day AIs will be able to participate in cultural practices like humans do, as sentient beings, but current generative AI models do not.

> That is not a water bottle, it's a domesticated puddle. Many (most?) people don't care about the artists behind songs (even less so about their culture). They care about the "organised sound" being enjoyable to hear. And to them, AI music is just as valuable as manual music. Gangam style didn't become popular because people cared about PSY. It didn't become popular because of its thoughtful lyrics and insightful me…

> They care about the "organised sound" being enjoyable to hear.

"Enjoyable to hear" is a problem that has been solved since the paleolithic. Musical scales and modes have always been a thing, making sounds that are nice and harmonic is a straightforward mathematical problem.

Re: DeepMind releases Lyria 2 music generation model

#267

Post by qwertox »

antononcube wrote: post #110

The creation of music by AI brings to mind a quote from David Bowie: “Music itself is going to become like running water or electricity. So take advantage of these last few years, because this will never happen again. Get ready for a lot of touring, because that's the only unique experience left.” While Bowie had different reasoning for making that statement, it's interesting to think that with AI-generated music, hi…

There are things which are just "musician things". An AI just can't replace it.

Like the performance of "Hania Rani live at Invalides in Paris, France for Cercle" [0]

This is what makes a musician.

[0] https://www.youtube.com/watch?v=J5oZ80Daduc&t=2145s

Re: DeepMind releases Lyria 2 music generation model

#268

Post by littlestymaar »

antononcube wrote: post #110

The creation of music by AI brings to mind a quote from David Bowie: “Music itself is going to become like running water or electricity. So take advantage of these last few years, because this will never happen again. Get ready for a lot of touring, because that's the only unique experience left.” While Bowie had different reasoning for making that statement, it's interesting to think that with AI-generated music, hi…

It has been the case for at least 15 years with the rise of Spotify/Deezer and we could even argue that it started with the first mp3 players with pirated music libraries.

Re: DeepMind releases Lyria 2 music generation model

#269

Post by tarcon »

magic_hamster wrote: post #186
SequoiaHope wrote: post #169

Earlier quoted context omitted.

The reason you don’t have more time for music is not technological, it’s social. We have enough technology to offer a basic life for everyone for free, but we have not agreed that doing so is worthwhile.

Who is "we"? The entire human race? Expecting all humans across different cultures and languages to come together and figure out basic income for 9 billion people is absurd. This kind of cooperation never happened and probably never will. People are completely unable to cooperate at the massive scale this requires, let alone solve far smaller challenges like mitigating outbreaks or making an effort to avert climate c…

The first step towards this is a UN resolution.

Re: DeepMind releases Lyria 2 music generation model

#270

Post by awongh »

magic_hamster wrote: post #186
SequoiaHope wrote: post #169

Earlier quoted context omitted.

The reason you don’t have more time for music is not technological, it’s social. We have enough technology to offer a basic life for everyone for free, but we have not agreed that doing so is worthwhile.

Who is "we"? The entire human race? Expecting all humans across different cultures and languages to come together and figure out basic income for 9 billion people is absurd. This kind of cooperation never happened and probably never will. People are completely unable to cooperate at the massive scale this requires, let alone solve far smaller challenges like mitigating outbreaks or making an effort to avert climate c…

We as in, it's not a social cooperation thing, many people's individual moral ethics make it so they themselves would be uncomfortable with the idea of not working to earn a living. Currently, society as a whole generally believes that it's each individual person's prerogative to find paying work and most people don't really examine this belief. There's nothing to cooperate on yet.
Post reply on HN