I have a very pragmatic view on music: all I care about is whether it sounds good or not. That’s it. That’s literally it. And from that standpoint the advent of AI music has been a major net positive for me.
You can choose to ignore that and come tell me about the ethics of using AI or how you care about the story behind the song and so on and that’s all fine but just note that you’re no longer addressing what I’m actually saying here.
I’m also not claiming it’s great - only that it’s good. I’ve yet to discover an AI song that I go back to like I do with many human-made songs but if I want to put on a playlist playing in the background then one consisting of entirely AI-made music reliably provides me well above average track after another whereas with organic music I need to sift through a ton of absolute crap to stumble upon the occasional good track that still rarely exceeds what AI is able to output. I can go on YouTube and put on a 2 hour playlist of Jazz House or similar and I don’t get the urge to skip a single track.
Currently I feel like where AI still trips is lyrics - they still are only plausible sounding nonsense once you actually start paying attention to it but especially for instrumental music it has far exceeded the level of a good average human artist.
Few examples of what I’m refering to: with vocals and without.
“it’s just sounds”
So, straying from the conversation about AI music being good or whatever. This is the part of AI music that perplexes me the most. So like… Audio is a wave. You can take a sine wave, and a square wave and layer them on top and you get a sine wave with some square edges because it’s both sounds. Different frequencies for different pitches, all of that.
When AI makes music, is it just drawing that wave? If so, that’s fucking crazy. Like I could understand if it used some ingested music theory to write chords and a melody, then turn them into MIDI, then run those through a synth plugin. But AI doesn’t have a synth plugn. It just knows what a synth plugin sounds like through analasys of sound waves, right? Like AI can’t “hear” music. It doesn’t know what a cello sounds like. It just knows what the sample point values of a waveform of a cello sounds like. But then if you tell the AI to add an instrument. Let’s say an electric guitar. It knows how to re-draw that wave to actually make that sound. To add reverb? To add compression? Then more instruments?
If that’s how it actually works, that blows my god damned mind. No human could ever write a song by drawing a line on paper and scanning it in. I suppose they could, but it would be some avant garde experimental thing, not something that sounds like actual instruments. Like I don’t think a human could ever figure out how to draw the sound of fingers sliding down the frets of an acoustic guitar between the actually strumming of a guitar.
It’s fucking bonkers.