I also liked that it didn't explicitly say how it decides when to play a note.
All the subway routes are normalized to 15 seconds long from beginning to end. The app then plays all 15 second routes together, playing the instrument assigned to the route when there's a train there.
Neat commentary on the instruments that were assigned to the route when you mouse over it.
But then, jazz is sometimes spoken of as expressing the rhythms, sounds, and emotions of the modern city.
The idea is novel/fun/cool, but the notes ARE random as far as we can tell. So if you're against AI music, you just like the idea but don't care about the music or... something else I can't imagine.
I think we can all come up with a bunch of original "hey, if we turn this random pattern of X into music, it would be interesting". But I don't see the point of actually doing it since the result is obviously going to be random uninteresting notes. If I convert my keypresses on my keyboard over the past year or whether my dog licks itself or barks or runs into music, it would still be random crap. The idea of the article is the only thing that made me go "huh" for a few moments. Clicking around and seeing the execution and hearing the music was definitely "meh".
Enlighten me, please.
There are variations as trains run fast or slow or not at all. Even those events are results of causes.
It might not be repeatable or predictable but it is not random.
Also, an artist made this. I can appreciate the design and flair of another human. AI is soulless. And there was a nothing to celebrate. No one to clap on the back and say “good job”. No one to identify with and say “people are really neat.”
Bolero is an amazing piece of music. Ravel’s brain was suffering from a degenerative disease at the time. We would not have Bolero without his disease. That fact to me turns the piece of music into a meditation on what his mind may have been like. What it might have been to be Ravel.
I don't think anyone will listen to this for the pleasure of listening to music.
AI crap can be much more listenable-as-music but nobody likes the process or the product.
Yeah, it's better than a lot of people, but it doesn't deliver the "just as good" part. On top of that you get that now anyone can promp a song and have a deluge of grey, tasteless elevator music.
It's not because AI-generated music inherently sucks. It's generally C-grade professional music. It's just not novel or especially interesting, and the low barrier to entry means there's a ton of slop in the space.
A lot of people have always wanted to make music, never made it past the barrier of "music is hard," and therefore have no clue as to what makes truly good music. And now that they have AI, they think they can just skip all the boring parts and make great songs.
And while they can skip a lot of steps in the creative process — those skipped steps also help musicians develop their artistic taste and judgment.
And just because these AI "creators" can't tell the difference, they assume others can't either. And then they get mad when critics recognize their uninspired, derivative slop for what it is.
That's not limited to music, either. You see it in coding, graphic design, writing, and pretty much any other LLM-assisted content generation. Maybe it'll change one day as models get better. Maybe not.
This project is original, stylish, technically clever, aesthetically pleasing, and well-crafted. There's a level of polish and intention behind it, and people here recognize that.
Every dot is a real subway train. Eight hundred of them, give or take, form a small jazz combo (walking bass, piano, sax, vibes, brushes) that has been playing without pause for over a hundred years. On the platforms they are hot, screaming, full of complaint. This is the music inside the noise.
The harmony moves through a slow chorus. A note is placed precisely where the train happens to be along its route. Rush hour fills the band with held tones; at 3 a.m. the silences grow longer. Whatever is playing now has not played before and will not play again.
Share your location and the trains nearest you grow louder. The piece rearranges itself around your body. You are listening to a portrait of where you stand, played by the city you are standing in.
I imagine for some genres it would be easy to recognize it as slop, but not as easily for others. It's intuitive techno would be easier to make than trance, which would in turn be easier to make than nu metal.
Can you share some AI music, if you've kept track of it, that's the hardest for you to recognize as unimaginative slop? I'm genuinely interested in how it would sound to me.
Of course music can be worse than random: it can be annoying.
I get a downvote, huh? Look, I like Ornette Coleman. I like Nurse With Wound and Merzbow and avant-garde noise. I do not like 21st century pop. If I have to have music played to me against my will, I would way prefer it to be random notes than if it presented a slimy modern personality, or used a tone of voice to sing at me with, or conveyed vapid little bad ideas in its lyrics.
That's how I feel with most art - "yeah, it's cool, but can I look at something else now?". The time someone spent on creating it seems disproportionate to the time I'd interact with it. Maybe since lots of people will interact with it, it makes sense to do it, but maybe I just don't get art at all.
I see some sculptures that seem really basic, like putting some stones in some metal cage or something equally easy to design or, at least, explain/communicate. And all I'm thinking is "they paid some people to move a few tons of stone and weld some metal rods together... for this?!". My feeling is similar here - the idea is neat(ish) but someone went to all the trouble to actually implement it? The implementation gives us this random music we can play in our browsers but people mention they care more about the concept than the music. So why go to all the trouble to make the final polished version of your idea? Why not just say "imagine if we mapped the trains' locations via gps at specific times to different instruments"?
Yeah, I probably don't get art as others do. I just don't see a difference between "imagine a 100-ton stone handing from a rod" and "look at this actual 100-ton stone hanging from a rod".
This was actually preferable to genuine pop music, because it didn't demand much of my attention, and was closer to silence, which would have been perfection. But it wasn't communicating anything. Communicating is an imposition, and a risk.
I don't know, I have some sympathy. Conceptual art is kind of meh. Travel is pointless, everywhere is the same, you can read about places and stay home, everything is unnecessary. Except I'm probably wrong.
For traveling it's very similar. I've seen some monuments in pictures first and in real life later. When I see them IRL, it's just... meh. Maybe I've been desensitized to giant structures or to how much detailed a sculpture can be, but even if I realize I have been, the "damage" is done. I can't be in awe of something someone 300 years would find awesome. I can just think "Why did I waste X hours to see this in person?".
That's why I don't really travel anymore. I can get so much information about architecture or statues or nature from photos and videos that seeing the real thing would almost surely be a disappointment. Both the pictures and videos and the real things involve sight and maybe hearing. It's not like I'm reading about a recipe but not being able to taste the real thing.