What’s the difference? Why isn’t it seen as a collaboration between the person writing the prompt (using a scripting language) and the programmer/designer of the generation software and curator of the Data set?
I’m not sure I entirely follow you (I’m only half awake, sorry), but programmed music is only generated by computers insofar the computer is generating 44100 samples every second based on a set of mathematical rules the composer made. AI music is generated based on huge datasets and probability; the composer has very little to no specific control.
If I program a instrument/synth in Supercollidor or Pure Data or some hardware synth, and then sample the instrument/synth or create and sequence a melody for it on my MIDI (piano) keyboard or Schism Tracker, etc., I have complete and absolute control over everything, down to the very waveform. In that case I am truly and purely the creator of the piece.
If I type in a prompt, I am just playing a probability lottery. I have done jack shit more than describing a piece of music.
I might have misunderstood you though. For now, I’m going to bed. Good night!
First read this post I already wrote (TL;DR : the software he used was software for generating music, not writing a composition) : https://lemmy.world/post/32532002/18110617
Second, apologies for mixing metaphors and rambling about many things at the same time that are similar. The callout about synthesisers is about them reducing band sizes, not about composition.
If I program a instrument/synth in Supercollidor or Pure Data or some hardware synth, and then sample the instrument/synth or create and sequence a melody for it on my MIDI (piano) keyboard or Schism Tracker, etc., I have complete and absolute control over everything, down to the very waveform. In that case I am truly and purely the creator of the piece.
I agree with this complely.
Brian Eno literally created ambient music with algorithms like that, but it is still his creative work.>
If I type in a prompt, I am just playing a probability lottery. I have done jack shit more than describing a piece of music.
This is the center of the kind of point I’m trying to get to with John Cage and Brian Eno. They made partially completed pieces that were to be re-assembled algorhymically by machines later on, giving up complete creation of authorship to an inhuman entity. Tie that to :
Why isn’t it seen as a collaboration between the person writing the prompt (using a scripting language) and the programmer/designer of the generation software and curator of the Data set?
There are very structured and algorithm based ways of writing music , that can be automated in a computer, and varied with parameters. Composers/programmers were already doing this in experimental music. They do , and continue to do it in video games with dynamic soundtracks that react to combat intensity. What’s the difference between these and writing a prompt that says “generate a 3 minute song based off a popular jazz standard chord progression, instead of saxophones use Neys, instead of a double bass use a church organ, make the drums sound like they are from the 1900s, use the song stucture of intro-chorus-interlude-chorus-solo-outro , set the tempo to 150 bpm but make it get faster between structure changes, and use 4/4 time for the intro, swing in the rest.”
Do I have to go record several pieces of music or have a synthesiser play through variations of the chord progressions, cut them up and roll a dice by hand for it to be my composition?
The core idea is that record executives have been doing that since pop music existed. No one involved in the process wanted anything other than to make money. It’s the same fucking picture. No one gave a damn before, but now they do. It seems stupid to not care back then.
What’s the difference? Why isn’t it seen as a collaboration between the person writing the prompt (using a scripting language) and the programmer/designer of the generation software and curator of the Data set?
I’m not sure I entirely follow you (I’m only half awake, sorry), but programmed music is only generated by computers insofar the computer is generating 44100 samples every second based on a set of mathematical rules the composer made. AI music is generated based on huge datasets and probability; the composer has very little to no specific control.
If I program a instrument/synth in Supercollidor or Pure Data or some hardware synth, and then sample the instrument/synth or create and sequence a melody for it on my MIDI (piano) keyboard or Schism Tracker, etc., I have complete and absolute control over everything, down to the very waveform. In that case I am truly and purely the creator of the piece.
If I type in a prompt, I am just playing a probability lottery. I have done jack shit more than describing a piece of music.
I might have misunderstood you though. For now, I’m going to bed. Good night!
First read this post I already wrote (TL;DR : the software he used was software for generating music, not writing a composition) : https://lemmy.world/post/32532002/18110617
Second, apologies for mixing metaphors and rambling about many things at the same time that are similar. The callout about synthesisers is about them reducing band sizes, not about composition.
I agree with this complely.
This is the center of the kind of point I’m trying to get to with John Cage and Brian Eno. They made partially completed pieces that were to be re-assembled algorhymically by machines later on, giving up complete creation of authorship to an inhuman entity. Tie that to :
There are very structured and algorithm based ways of writing music , that can be automated in a computer, and varied with parameters. Composers/programmers were already doing this in experimental music. They do , and continue to do it in video games with dynamic soundtracks that react to combat intensity. What’s the difference between these and writing a prompt that says “generate a 3 minute song based off a popular jazz standard chord progression, instead of saxophones use Neys, instead of a double bass use a church organ, make the drums sound like they are from the 1900s, use the song stucture of intro-chorus-interlude-chorus-solo-outro , set the tempo to 150 bpm but make it get faster between structure changes, and use 4/4 time for the intro, swing in the rest.”
Do I have to go record several pieces of music or have a synthesiser play through variations of the chord progressions, cut them up and roll a dice by hand for it to be my composition?
The core idea is that record executives have been doing that since pop music existed. No one involved in the process wanted anything other than to make money. It’s the same fucking picture. No one gave a damn before, but now they do. It seems stupid to not care back then.