pouët.net

absolutely yes.

here's a (just for fun) video I recorded the other day while trying out Synplant 2 (it's a relatively simple synth that lets you load a sample, then approximates it via "AI") (cheers to @Twilight for the recommendation).

while you need crowd-sourcing for "natural" inputs, building a network for *procedural* sources can be fully automated.

sure, it's still computationally expensive (50k+ iterations needed for learning) but it's doable even if your name ain't Google or Meta.

p.s.: I have to add that I'm still in the "meh, why let the machine spend countless hours on sth I have to post-edit and can do myself in less time" camp so I put this (todo) on the back burner.

It is "teh future", though. Kudos, Sonic Charge, for leading the pack ! (it's a 10+ year dev effort, though, nothing quite so "easy")

When I first saw Synplant 2 it made me sad. You can either spend years (or your whole life) learning, perfecting your sound design or you can just let Synplant analyze Eno’s sounds and recreate them. Not only you don’t need to understand how these sounds are made, but Synplant doesn’t understand either. Sure, it may sound great to some. Progress. What bothers me about this whole tech is the input / training data. Input / training data is never a number, never an idea, a formula, algorithm. It’s never driven by users ingenuity. Input is always a finished, produced work of a human or a whole crew, while training data is a whole “cultural history” in a sense. Be it images, videos, sounds. All of this data is taken without consent. When using these things you’re not standing on the shoulders of giants, you’re pissing all over the giants. But, let’s put the ethics aside for a sec. Who will be filling the new book of “cultural history” if all creation moves to analyzing what’s there and recreating it. Many of the now iconic sounds came to be by happy accidents. For happy accidents you have to fiddle. Not with parameters of an AI “synth” but with parameters of sound design, with oscillators, routing, fx, feedbacks, whatnot. The first crop of regurgitation came in the way of sampling. But you have to clear the samples or at least credit them. Well, not anymore. Excuse me for not seeing this as progress. Same thing with images.

You know, that's a really big IF.

@Krill:
That’s right! That’s why I (and a lot of others) squirm and fight. To make the “IF” bigger. If we just stand and watch (or even applaud) then there’s no “IF”, it’s dead certain. My personal (of course highly inacurate) prediction is that the internet as you and me know it is going to consist of something like 90% of “AI” created content by this time next year. Or the next. Consequences? I don’t know. Look how it changed Google search by now. Shitty GPT made fake “websites” pop in the top 10. On any topic. It got very hard to find the real good stuff. And this is just the beginning of the real beginning.

Do what you must, even if it's making a really big IF even bigger. :)

One can always hope. In reality however, all chances are our collective squirming makes no difference.

more AI crap of mine (follow me) : https://www.instagram.com/latentspacecadet/