Might top-tier AI musicians hit the scene before extremely low-friction production tools take off?
-
This Tweet is unavailable.
-
-
Replying to @webdevMason @danielgross
If some kinds of original beautiful (or at least enjoyed) music doesn’t require genuine creativity, ok. But that’s quite a claim: trial and error over the space of audible sound is possibly what human composers do. Though I’d guess it’s that and then some.
@dela3499 ?2 replies 0 retweets 1 like -
Musicians usually think in terms of notes, melodies, chords, effects, and things like that. It’s a very limited subset of all possible sounds. One can build these ideas into tools like a piano or https://youtu.be/1iZa0-U27dc , so even the proverbial monkey at a typewriter sounds okay.
1 reply 0 retweets 2 likes -
So you can imagine an algorithm that somewhat efficiently somewhat reliably could be specialised to generate good music?
1 reply 0 retweets 0 likes -
Yeah. (e.g. play arpeggios of equally spaced notes from random chords all from the same randomly-selected key)
2 replies 0 retweets 1 like -
Replying to @dela3499 @ToKTeacher and
I think you can create something that *sounds* good in that way, however that is because we have heard it before so it is not something new. There is a difference between music *sounding* good and being objectively good. Creating the latter is hard
1 reply 0 retweets 1 like -
Replying to @ernsterlanson @dela3499 and
Again: I admit vast ignorance here. But it seems analogous to AI visual art. You may get pretty patterns via following an algorithm (I recall when "visualisers" were popular in Apple and Microsoft music players). I mean: pretty to look at. But: original art? Actual creativity?
1 reply 0 retweets 2 likes -
Replying to @ToKTeacher @ernsterlanson and
Not creative currently, whether it is generative art or generative music. The programming that causes such pretty phenomena cannot critique its own efforts - past, present, and future - unless a skilled enough programmer supplies the prerequisite "instruction from without".
2 replies 1 retweet 3 likes -
Replying to @adilzeshan @ToKTeacher and
Yeah, the question isn’t really about whether a program can make something that sounds good. It’s “What does the program do when it confronts a musical problem - when something sounds bad?”
2 replies 0 retweets 3 likes
I'm having a really difficult time mapping any of these concerns/assumed limitations to the actual process of e.g. training a neural net. Do you need human feedback? Yes. But that's exactly what platforms like Instagram & Soundcloud are for
-
-
Replying to @webdevMason @dela3499 and
It’s a philosophical question: can an algorithm be written such that largely *absent frequent human interventions* good music can be produced (in other words: some kind of automated composition). No problem with the idea that *with human creative input/feedback* it’s possible.
1 reply 0 retweets 1 like -
Replying to @ToKTeacher @dela3499 and
Humans broadly suck without external human feedback, too
1 reply 1 retweet 1 like - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.