You must log in or # to comment.
Music discovery algorithms don’t have to be AI slop. Some of them used to work effectively peer to peer based on likes.
You like songs, as does everyone else. The algorithm compares the songs you liked to what other people liked, finds people who liked a high percentage of the things you did, and recommends you other songs that they liked, and vice versa. Basically “Many people who liked [song you like] also liked [song you maybe haven’t heard]”.
I can recommend Listenbrainz as a recommendation service.
Sadly once you like one song that’s been on the radio once, it starts spiralling into other songs (often good even) you know from the radio and 0 other songs. With things that kind of come in sets (like “songs that played often on X channel in the 90s”) it becomes quickly a game of complete the set rather than discovering new music you’d also like.
this is my annoyance too
There collaborative filtering algorithms do tend to have a popularity bias. The other downside is that these algorithms also don’t help new music and musicians get found.
Yes, though I’d argue that’s the same downside :D
I’ve worked in recommender systems for news specifically myself for a couple years so if anyone has some questions that aren’t too identifiable, AMA I guess
We had a system that combined your reading history (from a tracking pipeline that already existed similar to google analytics) (though it could have just as easily been sent from the front-end with the request for recommendations as we didn’t precompute anything) with several scoring systems (from simple things like popularity score per article which ignores your history, to multiple complex pretrained models that use your history to calculate a score optimising for some variable), all of which can be weighed and then the scores are added/multiplied and sorted and bam, out rolls your personal list of recommendations.
We could easily tone down (even turn negative) the populatity bias, but it turned out that it was just a strong predictor for what people wanted to read (measured in both click through rate and dwell time on the clicked page), so we’re not entirely sure whether news is just different (if you spent a couple of minutes per day scrolling past headlines you’ll have seen everything from today, and clicked what you cared about, and left again) or we weren’t really catering to the crowd that would be helped by getting non-popular recommendations, because they’re drowned out by the crowd that’s just looking for whatever’s popular.
Anyway, AMA
I said “via algorithms and AI slop”, two seperate ways of finding music, “AI slop” meaning Spotify-style playlist nonsense.
Also, algorithms create feedback loops, where popular things get recommended more, even among specific niches.
True. But even that can be tackled in recommendation algorithms (or attempted). The main issue I see is that the companies that produce them don’t have their goals aligned with yours and rerank results to benefit their bottom line. That said, I’ve gotten much better recommendations for books, music and games from people online and friends than from any such system. Worst case the recommendation is not great and that is still an opportunity to talk to the person who recommended it.
With respect, that’s a bit like saying twitter doesn’t have to be a far right hate speech enabler. What something is, and what something could be, I’m afraid in this case are irreconcilable.
Everything a computer does may as well be magic to 99.9% of people.
Youtube’s algo has been pretty good at giving me artist/song recommendations… admittwdly after over a decade of liking and subscribing to a ton of bands on the platform. Brought me IDLES and Viagra Boys first LPs before anyone else, and just this week turned me on to Vancouver band PISS. They’re fucking raw, take heed of the lead’s warning before they start.
Same. Over the last decade that was one of my main main ways of finding new music. Don’t really had friends with similar tastes and record labels luckily all had official accounts. Plus promotion accounts who upload music from certain genres. There are definitely genres I found via the algorithm.
music discovery via the internet archive tags
edit because i saw people posting reccomendations: (some random polish 90s punk) https://archive.org/details/Apatia_Odejdz-Lub-Zostan/
Discovery, by Daft Punk (☞ﾟヮﾟ)☞
If someone don’t know, it’s an album name, alternatively known with music-video movie “Interstella 5555: The 5tory of the 5ecret 5tar 5ystem”, basically a music-video for whole album, bit anime.
Daft Punk is the best! I’ll have to check out this movie thing :3
Thanks!
Don’t forget music blogs and reviewers (which may technically fall under “randos”). In this age of bland algorithmic recommendations, going back to reading articles and reviews written by someone with similar musical tastes has once again become my favorite way to discover new music.
Oh yeah, I bet that’s a good way too! I’ve never considered that before tbh. Maybe I’ll look into it.
So now I need to discover good blogs (or blog posts) to discover good music 🤔
I mostly use bandcamp tags, which works better than you’d expect.
Anyway, you should check out Carcosa.
Carcosa… The King in Yellow?
Well, the Canadian metal band, who probably named themselves after the book.
Wikipedia rabbitholing is my preferred method. Start on an article about a band or genre you like, then just glance through for influences and subgenres etc., read those articles to find new band names, give 'em a quick listen on whatever platform you use (usually just YouTube for me), and continue the process as needed i.e. if you don’t like what you hear for a given artist, just keep clicking till you find the next one. It sounds like it’d take forever this way, but I’ve found new bands I love within about 10 minutes of clicking, and this is consistently the case. Algorithms have never, ever recommended me anything I actually liked, and this is true for music, games, TV shows and whatever else. They just don’t work on any meaningful level.
But this only gets you some of the larger bands. Many of the bands I listen to have no wikipedia article or even much of an online presence outside of instagram or facebook to announce gigs and shows
This is kinda genius. I’m gonna try it lol
Mwahahahaha my evil plan to get more good songs is working >:3
Neil Cicierega’s Mouth Albums are all fire.
Triple-Q makes some real solid bangers.
I just listened to Mouth Moods this morning, it still slaps!
Dungeon synth
Ohhh I’ve read about dungeon synth! Or maybe I watched a video? I can’t remember. I really should give it a try. Thanks!
Seeing who’s playing with bands you like can be an inspiration. That’s how I found Slothrust, years ago.
Ok online randos, recommend something like https://www.youtube.com/watch?v=6HYHdkEYdQE Please
This seems pretty similar:
(Just kidding, just kidding (mostly))
My playlist hasn’t been updated since the late 90s.
Me fr. I bet I could craft the perfect playlist, and never listen to anything else again. That actually sounds like pretty fun idea… maybe i could make a mixtape…
Ah, I used to have a transparent tape deck/radio. It was the height of 90s coolness.
Omg I love transparent electronics; they’re such a vibe! I might actually look for a second-hand one. It truly is peak coolness.
Check out Heyoka if you like punk/metal ans don’t mind it being french. They have a cover of El Pueblo Unido which is pretty fire. Idk why a French band covered a spanish song but I fw it
Thank you for the recommendation, comrade.
Omg I’m stealing th—
…
I guess it’s for sharing, isn’t it? lol
This is the way.
