Live data from Hacker News

DeepMind releases Lyria 2 music generation model

deepmind.google

51–60 of 444 posts

Re: DeepMind releases Lyria 2 music generation model

#51
post #4

Only available in the US "Country of residence (this current phase of the experiment is only available to users based in the U.S. for now, but feel free to submit interest and stay tuned for updates): "

I remember when they made some generative AI chess demo and when I went to visit it, it said it's not available to users under 18 or outside US. And I had to do a double-take at the idea of chess that is 18+ and georestricted

Re: DeepMind releases Lyria 2 music generation model

#52

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)

Re: DeepMind releases Lyria 2 music generation model

#53

I've made a few tracks using Suno to scratch my own itch / desire for music that covers certain themes. The best use of Suno for has been the ease with which you can generate diss tracks: I ask Gemini to make a diss track lyrics related to specific topics, and then I have Suno generate the actual track. It's very cathartic when you're sitting at home in the dark because the power company continues to fail. Anyway, I…

> Why aren't the people who build these tools innovating more? We’re getting access to generative AI tech and people are looking for innovation in the UI? I mean I get the need for UX but it’s probably coming man, what with MVPs and all

I think producing new and interesting music with AI tools will require models that allow for far more granularity, tweaking multiple tracks / layers, and this has to be exposed through a more professional and capable UI. It has to go hand-in-hand if it's going to be treated as anything other than a novelty or a toy.

Vibe coding has improved significantly in tandem with UI innovations that provide a more intuitive interface to the workflow. Although in the vibe coding space there's still a lot of room for innovation and exploration, especially when doing detailed task development.

Re: DeepMind releases Lyria 2 music generation model

#54
post #52

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)

I guess automatic sorting, washing at the right temperature, drying and maybe folding is what someone who washes their own clothes would wish for.

Talking to the appliance is probably not that high on their list.

Re: DeepMind releases Lyria 2 music generation model

#55
post #46

Earlier quoted context omitted.

These are actually just the problems easier for researchers to solve, mostly due to a lot of readily available data.

Everyone shares music and art they make but nobody ever shares videos and motion capture of themselves doing laundry and vacuuming their house. Maybe we need to start sharing that instead

Check out the Epic Kitchens project, there are labeled video data sets of cooking, doing dishes, etc.

https://github.com/epic-kitchens

Re: DeepMind releases Lyria 2 music generation model

#56
post #15

Earlier quoted context omitted.

Nothing stops you from doing art and writing, just like nothing is stopping someone today from riding a horse, running a marathon or rowing a boat.

Presumably, the idea is that AI drives down the cost (and thus, value / career prospects) of art and writing.

I'm gonna be honest... Very few people are artists for the pay

Re: DeepMind releases Lyria 2 music generation model

#57
Ai music has been awesome for me, not because the music is that good, but because it gives me the ability to do something that I couldn’t have done myself. I use it all the time for my DnD group, songs about characters, funny moments, backstories, it’s a great tool that our players have found to increase engagement with the game

Re: DeepMind releases Lyria 2 music generation model

#59

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

These are actually just the problems easier for researchers to solve, mostly due to a lot of readily available data.

That's indeed the second worst issue with current model architectures. For a model to be trained to something nearing usability for an actual task it needs an amount of data that is far beyond what can be obtained. Companies like Facebook and OpenAI downloaded pirated copies of every single book humans have written to reach the current level of text generation, and even with that, it's not like those models are perfect or that intelligent.

It is going to severely limit the possibilities of building actual agentic AIs. We do not have an endless amount of data of humans performing menial chores. And normal people will probably more hostile than the kool aid drinking software developers when it comes to being spied on, who's going to agree to wear a camera while working so as to help train their own replacement? Yet it's kinda what devs are doing gleefully adopting software filled with telemetry and interacting with copilot.

Re: DeepMind releases Lyria 2 music generation model

#60

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'm getting a little tired of hearing this quote at this point.

What about humoring the opposite?

I want AI to automate art so I can spend more time doing dishes and doing laundry. Dishes and laundry are purely analog human experiences. Art, at this point, is essentially digital, and digital is the domain of machines so we can let machines do that now.

Post reply on HN