Live data from Hacker News

DeepMind releases Lyria 2 music generation model

deepmind.google

121–130 of 444 posts

Re: DeepMind releases Lyria 2 music generation model

#121
post #15

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

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.

Stops you monetising it.

Re: DeepMind releases Lyria 2 music generation model

#122

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 don't think there would be any art or writing to do if there was absolutely no "laundry and dishes", conflict, either. The Wall-e future seems more consistent with that honestly, but maybe I'm just revealing an ugly part of my own personality

This is contradicted by the fact that, throughout history, there have been tons of rich people who not even once had to do laundry or any other menial tasks.

Many of them were interested in art or produced it. And many led fulfilling lives without getting depressed from not working as some people fear.

Re: DeepMind releases Lyria 2 music generation model

#123
post #97

Earlier quoted context omitted.

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 colonizati…

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

Exactly. The thought of spending hours on something that an AI could do in minutes sounds horrible to me.

Re: DeepMind releases Lyria 2 music generation model

#125
post #6

It seems to struggle to create music with a strong identity. It is great if you want to make a poor imitation of top 40 hits. But the thing about top 40 type music is that the best music is already in the Top 40. It remains to be seen if there is as strong a demand for a music chart filled with slop as there is demand for a music chart filled with pop tunes by celebrities. I don't think audio files are the right outp…

Since we've already evaluated - let's exaggerate - that "most Top 40 songs are slop", maybe lyrics are a big factor in creating identity? I mean, it's true for books, right? I could easily imagine an AI-generated Top 40 song that people would still describe as having a unique identity.

I'm not super into the topic, but let me give you two niche examples that are definitely not Top 40 material, yet are considered to have a strong identity within their communities.

I guess one of the reasons the game Yasuke Simulator has like 10x more sales (don't pin me down on that) on Steam than the actual game Assassin's Creed: Shadows is its very catchy soundtrack, with lyrics that are funny and strongly aligned with the content. [0]

Another example, not focused on lyrics and from a completely different niche genre, is this jazzy death metal song that was particularly well received, not only because of the intentionally hallucinatory video. One could even argue that the hallucination is perceived as a feature, not a bug. So why shouldn't the same be true for audio? [1]

[0]: https://www.youtube.com/watch?v=Hkh38jhILec

[1]: https://www.youtube.com/watch?v=OzXafFUekl0

Re: DeepMind releases Lyria 2 music generation model

#126
post #42

Earlier quoted context omitted.

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.…

Who is the work for? If I lived in the automated future (or could afford private staff in the present) I would do more creative stuff just because I enjoy it and with no expectation of having an audience. For context, I'm an occasionally-published photographer, and I like playing piano but I'm not at a level anyone else would want to listen to.

Re: DeepMind releases Lyria 2 music generation model

#127
Strong opinion ahead: the very moment people will finally realize that music is in the microscopic nuances of the human touch, breath and taste(literally for every instrument), hopefully we will get disinvested in this useless technology. Yes, I am aware of software like pro tools, but that can ba used well for touch up all tue nueances

Re: DeepMind releases Lyria 2 music generation model

#128
post #106
post #48

https://deepmind.google/technologies/lyria/ Lyria 2 is currently available to a limited number of trusted testers

Yep not going to bother reading these hype advertisements about things that are not even available. This sucks so much from Google.

TBH at this point HN should have a flag for "No Demo"

Re: DeepMind releases Lyria 2 music generation model

#129
post #35

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

The last 5 years have been a supersized lesson in Moravec’s paradox [1]. More people need to hear about this: the tech world doesn’t have some kind of conspiracy against the creative class, it literally is the lowest hanging fruit as predicted 30 years ago. [1] https://en.m.wikipedia.org/wiki/Moravec%27s_paradox

Who said anything about conspiracies?

Re: DeepMind releases Lyria 2 music generation model

#130
post #59

Earlier quoted context omitted.

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 perfe…

There will be no difficulty equipping people in minimum wage jobs with cameras. You could probably even get companies to pay to give you training data, if you sell it as an AI-powered system for reducing shrinkage or avoiding liability. The most likely source of pushback (that companies will care about) is likely to be from customers interacting with people wearing cameras, so it might be limited to non-customer-facing roles.

Another good source of data would be exoskeletons, though I don't know that any of those have actual seen real commercial success yet.

Post reply on HN