this post was submitted on 01 Jan 2026
21 points (100.0% liked)

technology

24155 readers
106 users here now

On the road to fully automated luxury gay space communism.

Spreading Linux propaganda since 2020

Rules:

founded 5 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] Awoo@hexbear.net 5 points 1 week ago* (last edited 1 week ago) (3 children)

I know it won't be popular to say this here but I think AI music is going to eventually reach a point where it is capable of doing something interesting.

What it needs in order to do that however is to merge biological data with what it does. If you start feeding in heart rate, sweat and other data into machine learning on top of generation it will eventually find some genuinely interesting ways to use sound and music to manipulate biological response.

That might not even sound like music as we know it though so it will be interesting in and of itself.

Ultimately generative AI without that data is going to be at a permanent disadvantage to human creators who are using their knowledge of biological response to music when composing. It's a logical step I think we'll see.

[–] TheFinalCapitalist@hexbear.net 11 points 1 week ago

Sorry after reading all of this, all I can think of is ai coming up with its own brown note

[–] Le_Wokisme@hexbear.net 6 points 1 week ago (2 children)

adaptive procedural music isn't strictly something you need generative ai to create. that could literally be an apple watch app or some shit with normal programming practices.

as far as the generative stuff goes, i'm the most interested in the unintended results and failure modes, things people would never deliberately make. that would be better than algorithmic pop garbage

[–] Meltyheartlove@hexbear.net 3 points 1 week ago (1 children)

Something like this https://generative.fm/ or maybe something coded with supercollider, sonicpi, faust or something.

[–] Le_Wokisme@hexbear.net 3 points 1 week ago

exactly. i wouldn't even be surprised if the biometrics-informed version has been done and most of us never heard of it because we wouldn't think to look for it

[–] Awoo@hexbear.net 2 points 1 week ago* (last edited 1 week ago)

Yeah I'm talking about the AI creating something that does not exist or at least using what exists in a way that absolutely optimises emotional effect in a way that a human being can't without the realtime metrics. AI could theoretically not just make songs but make songs in realtime based on the response it is getting from the listener. This is inherently not something a human musician is capable of doing.

At that point I think I'm talking about music having potential to be similar to drug effects though. Music already does affect me like a drug, changing my mood and emotions entirely, optimising that in realtime could go interesting places.

The interesting part of this is not AI making stuff that already exists though. It's the potential for doing something that does not currently exist. AI becomes genuinely interesting to me when it's pushing that frontier rather than rewriting what's already been done.

[–] Damarcusart@hexbear.net 4 points 1 week ago (1 children)

It's a tool, and like any tool, it needs the person using it to understand and appreciate the medium they're trying to work in, in order to create something genuinely unique. I don't think it will be capable of creating anything beyond the most generic, because the only people interested in using it are people who only want to make a quick buck and not actually express ideas creatively.

[–] Awoo@hexbear.net 3 points 1 week ago

You're not wrong