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

91–100 of 444 posts

Re: DeepMind releases Lyria 2 music generation model

#91

Post by thih9 »

koiueo wrote: post #52
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

> I want Al to do my laundry Do you want a washing machine with Alexa built-in? Be careful what you ask for. (I know what you meant, but the only laundry-related AI you can hope for, is a cloud connected smart speaker telling you it can't wash with unapproved third party detergent pods)

> the only laundry-related AI you can hope for, is a cloud connected smart speaker telling you it can't wash with unapproved third party detergent pods

This seems unnecessarily fatalist.

Laundry folding machines exist[1] and there were attempts to create a consumer friendly one, so far unsuccessful. Technology advancements could make that happen. At least that's what I'm hoping for.

[1]: https://en.wikipedia.org/wiki/Laundry-folding_machine

Re: DeepMind releases Lyria 2 music generation model

#92

Post by dist-epoch »

ipaddr wrote: post #21

The interest in ai music generation is lower than I initially thought. I jumped in but felt the exercise lacked the joy of making music physically or with software like pro tools. With pro tools you control the thousands of knobs which gives you more control. These AI models take away that connection. You can play around with different words to get different results but it's like painting with a shotgun. No one wants…

> No one wants to hear other people's ai songs because they lack meaning and novelty.

And hear I was thinking that many people listen to songs because they like the sounds of it, but apparently it needs to have "meaning".

Re: DeepMind releases Lyria 2 music generation model

#93

Post by collias »

I find this to be profoundly depressing.

I've just recently re-discovered the joy of writing my own songs, and playing them with (actual) instruments. It's something I get immense pleasure from, and for once, I'm actually getting some earned traction. In another life, I may have been a musician, and it's something I fantasize about regularly.

With all these AI-generated music tools, the world is about to be flooded with a ton of low-effort, low-quality music. It's going to to absolutely drown out anyone trying to make music honestly, and kill budding musicians in their crib.

I suppose this is the same existential crisis that other professions/skills are also going through now. The feeling of a loss of purpose, or a loss of a fantasy in learning a new skill and switching careers, is pretty devastating.

Re: DeepMind releases Lyria 2 music generation model

#94

Post by magackame »

amarant wrote: post #42
nurettin wrote: post #29

Earlier quoted context omitted.

Still a chore with the machine. It is implied that AI will take over the machines, collect your socks and shirts from around the house, put them in the machine, dry them out, iron them and put them back in the drawer in an energy efficient and hygienic way while you are happily painting.

It's still creative work to make music using AI too. In both cases, the machines just made it a lot easier

I am not too sure about that. Isn't the whole thing about art and music is that you can convey something that words cannot? Of course, these models start to support image and audio inputs as well, but the most interesting mixing step that happens in the artist's head seems missing in the generated output. If you have some vision inside your head, making something out of it by hand is still the best way to convey it. Just as writing something down refines the thoughts and reveals holes in your thinking - drawing something is visual thinking that reveals holes in your imagination. You can imagine some scene or an object pretty easily, but if you try to draw it into existence, you will immediately notice that a lot of detail is missing, a lot of stuff you didn't think through or didn't even notice was there at all. The same applies to creating music and programming. Using generative AI certainly has some artistic component to it, but I feel like using these models you give up too much expressive bandwidth and ability to reflect and take your time on the whole endeavor.

Re: DeepMind releases Lyria 2 music generation model

#95

Post by berkut »

collias wrote: post #93

I find this to be profoundly depressing. I've just recently re-discovered the joy of writing my own songs, and playing them with (actual) instruments. It's something I get immense pleasure from, and for once, I'm actually getting some earned traction. In another life, I may have been a musician, and it's something I fantasize about regularly. With all these AI-generated music tools, the world is about to be flooded w…

People also said similar things in the past (I'm a musician as well: guitar, piano and bass) about Synths and Drum machines (and things like GarageBand which can do backing drums and even basslines semi-automatically now).

Some of those things enabled others to create new types of music or express themselves in different ways.

Re: DeepMind releases Lyria 2 music generation model

#96

Post by summerlight »

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

Well you know, all those fun and creative parts in software engineering has been taken over by vibe coding and now humans are supposed to do only tedious works, so probably the same thing applies here.

Re: DeepMind releases Lyria 2 music generation model

#97

Post by dgfl »

voidspark wrote: post #73
Toenex wrote: post #71

Earlier quoted context omitted.

I want AI to be able to do everything so the I can choose to do anything.

If it can do everything, then you will be redundant.

I keep coming back to this thought. Maybe it’s how I was raised, but knowing that I’m doing something useful to other people / humanity is the entire point.

When a machine can do everything better than we can, then what do we derive meaning from?

I usually get out of the existential dread by thinking that we’re still some time away from the issue, and that there will still be some pursuits left, like space colonization. But it’s not fully satisfying.

Re: DeepMind releases Lyria 2 music generation model

#98

Post by vhcr »

CamperBob2 wrote: post #17
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.

Agreed to some extent, but I don't think you'll have too long to wait before that comes to pass. It can't possibly be that hard to build a model that will disassemble a given song into its original tracks, like a Fourier transform that yields drums, strings, keyboards, and vocals rather than sines and cosines. Equally unlikely that such a model will be too large to run locally. We will get some very cool tools -- and…

https://github.com/deezer/spleeter

https://github.com/facebookresearch/demucs

Re: DeepMind releases Lyria 2 music generation model

#99

Post by dodos »

collias wrote: post #93

I find this to be profoundly depressing. I've just recently re-discovered the joy of writing my own songs, and playing them with (actual) instruments. It's something I get immense pleasure from, and for once, I'm actually getting some earned traction. In another life, I may have been a musician, and it's something I fantasize about regularly. With all these AI-generated music tools, the world is about to be flooded w…

I feel its already hit the tipping point. I used to listen to mixes on youtube liberally, but I've now had to filter all searches to pre-2023 due to the flood of slop that's appeared. I used to finds loads of great up-coming musicians, but the amount of effort required to do so has increased considerably. I am tired of filtering out the slop.

Re: DeepMind releases Lyria 2 music generation model

#100

Post by vkou »

dist-epoch wrote: post #88
thrdbndndn wrote: post #61

Earlier quoted context omitted.

I'm not sure how this contradicts what they said. AI would likely lower the number of paid opportunities. Additionally, art requires practice. Sure, some "lower-tier" artists may produce work that AI could replace without anyone noticing. But by removing that step, we risk having fewer truly great artists emerging.

I will also be honest, if you expect to live off your art, you are doing it wrong.

If you expect to live off typing letters and numbers on a keyboard, (or off the labour of others, while you siphon up the lion's share of their productive surplus), you are doing it wrong.
Post reply on HN