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

Open-sourcing AudioCraft: Generative AI for audio

ai.meta.com

Post reply on HN
Print view View original

241–250 of 335 posts

Re: Open-sourcing AudioCraft: Generative AI for audio

#241

Post by cmgbhm »

PaulDavisThe1st wrote: post #92
manquer wrote: post #68

Earlier quoted context omitted.

Even before streaming, You never "owned" any music legally [1], you merely owned a physical copy of a performance[3] of a song, that in no way gives you the right to make derivative works [2] automatically. Also it doesn't really matter on what the law says, RIAA in the last iteration, relied on the fact it you would rather pay a fine than be able to afford expensive lawyers to fight the specifics out in court on ave…

Establishing derivation is at the crux of all legal matters surrounding diffusion models. It has not yet been clearly established. If it is, then I'd agree with you. Until then, I think it's a bit more up in the air. Also, IIRC, RIAA did not bring many resources to bear against e.g. "home taping" itself, because they could essentially never know that it had occured. The overwhelming majority of their efforts went int…

https://en.wikipedia.org/wiki/Audio_Home_Recording_Act

https://en.wikipedia.org/wiki/Home_Taping_Is_Killing_Music

Recording industries have fought end user reproduction often. They’ve fought sampling battles.

Go after the pocketbooks and go after the technology waves. If there’s a derivative argument they can make, they will.

Re: Open-sourcing AudioCraft: Generative AI for audio

#242

Post by cushpush »

Nice results so far. "Perfect for the beach" is a very funny description of music, because it has nothing to do with the acoustic qualities, so consider these descriptions to be anthropocentric! (As if they could be anything else) It is less about describing the actual sounds you want and more about describing the quality or vibe of the atmosphere. This is markedly different than incremental composition, maybe we can call it "composition by collage." Puts on COLLAGE shirt like in Animal House

Re: Open-sourcing AudioCraft: Generative AI for audio

#243

Post by vagab0nd »

bottlepalm wrote: post #102

Anyone feel like with the flood of AI generated content there's a risk of the past being 'erased'. Like in 10 years we won't be able to tell if any information from the past is real or fake - sounds, pictures, videos, etc.. Like we need to start cryptographically signing all content now if there's any hope of being able to verify it as 'real' 10 years from now.

Even with digital signatures, there are limits to what we can really verify.

We'll likely be able to verify whether an entity is a real human, using some kind of "proof of humanity" system.

We will have cameras/mics with private keys built-in. The content can be signed as it's produced. But in this case, what's stopping me from recording a fake recording?

Maybe it's a non-issue. We used text to record history and we've been able to manipulate that since, well, forever.

Re: Open-sourcing AudioCraft: Generative AI for audio

#245

Post by oceanplexian »

munificent wrote: post #188
RyanAdamas wrote: post #152

For my two cents; the goal of our human pursuit is to advance our technologies and systems to the point we can all live carefree lives where the focus of our pursuits is self defined. It is not to "own more rights" to shit. Sorry, but no one actually owns what they create, that's the point of creation. And if you take issue with the term create, that only reinforces my point. We're all influence machines, input and o…

> the goal of our human pursuit is to advance our technologies and systems to the point we can all live carefree lives where the focus of our pursuits is self defined. Agreed! > the future should not be about preserving some peoples rights to limit our collective advancements over their personal wants. Systems that don't allow people to extract value from the hard work they put into collective advancement do not seem…

> No one's going to spend all day making candy and put it in the "free candy" bowl when that one asshole kid down the street just takes all of the candy out of the bowl every single day.

Software is an infinite candy bowl. Taking candy out of the bowl does not take any candy from the person who made it.

Imagine if this was the physical world, and you had a machine that could end world hunger. You could copy food like you could copy and paste information on a computer. Imagine someone who would keep that machine to themself, out of a sense of entitlement to make a few bucks. Any person with any sense of morality can see the obvious problem with that.

Re: Open-sourcing AudioCraft: Generative AI for audio

#246

Post by btown »

mesebrec wrote: post #177
RobotToaster wrote: post #93

CC-BY-NC Isn't an open source licence, it violates point six of the open source definition https://opensource.org/osd/

Where does it say this is CC-BY-NC? The article says this: > Our audio research framework and training code is released under the MIT license to enable the broader community to reproduce and build on top of our work

It's pretty common in academic research for trained model weights to be licensed under something different from the code that one would run to create such a model if one had both sufficient compute resources and the same training dataset. That is, if those weights are ever released at all!

IMO, while I'd rather have one part permissively licensed than nothing at all... it stinks that companies sponsoring researchers get an un-nuanced level of street cred for "open sourcing" something that they know nobody will ever be able to reproduce because their data set and/or their compute grid's optimizations are proprietary.

As it stands, I'm not at all sure that the outputs of this model can be used for commercial videos.

Re: Open-sourcing AudioCraft: Generative AI for audio

#247

Post by brennanm »

squidsoup wrote: post #244

"Imagine a professional musician being able to explore new compositions without having to play a single note on an instrument." A musician will always reach for an instrument as their compositional tool - keyboard and mouse producers are not musicians.

This makes no sense.

How is pressing a key on a piano different from pressing a key on an electronic piano?

Re: Open-sourcing AudioCraft: Generative AI for audio

#248

Post by wpietri »

kmeisthax wrote: post #81
eropple wrote: post #34

Earlier quoted context omitted.

> MusicGen's weights are licensed CC-BY-NC, which is effectively a nonlicense as there is no noncommercial use you could make of an art generator How do you figure? Have you never just...made stuff to make stuff?

In copyright law the use of the work itself is considered a commercial benefit, so "noncommercial use" is an oxymoron. Consider these situations: - If I use AudioCraft to post freely-downloadable tracks on my SoundCloud, I still get the benefit of having a large audio catalog in my name, even if I'm not selling the individual tracks. I could later compose tracks on my own and ride off the exposure I got from posting…

What's your evidence for this bit?

> this is how judges will construe the license

Re: Open-sourcing AudioCraft: Generative AI for audio

#249

Post by squidsoup »

brennanm wrote: post #247
squidsoup wrote: post #244

"Imagine a professional musician being able to explore new compositions without having to play a single note on an instrument." A musician will always reach for an instrument as their compositional tool - keyboard and mouse producers are not musicians.

This makes no sense. How is pressing a key on a piano different from pressing a key on an electronic piano?

I was referring to a computer keyboard, not an electric piano. I can't see how any musician would see this appealing as a compositional tool. Music is its own language - expressing a musical idea with a text prompt is antithetical to the process of making music.

Re: Open-sourcing AudioCraft: Generative AI for audio

#250

Post by primitivesuave »

RyanAdamas wrote: post #152

For my two cents; the goal of our human pursuit is to advance our technologies and systems to the point we can all live carefree lives where the focus of our pursuits is self defined. It is not to "own more rights" to shit. Sorry, but no one actually owns what they create, that's the point of creation. And if you take issue with the term create, that only reinforces my point. We're all influence machines, input and o…

Creating something (writing a book, recording a song, etc) is a conversion of time (your only finite resource) into something of value (maybe only to you). It also turns out that having a profit motive and IP protection around creating valuable things is a fundamental requirement for having a creative industry to begin with. It's also what drives the free market to determine which creations are even valuable to begin with.
Post reply on HN