161–170 of 178 posts
The project has been packaged for a couple of distributions but you can also find it on github.
Earlier quoted context omitted.
> Weight follow on plays more highly What if I listen to Black Sabbath and then my niece wants to listen to the Peppa Pig soundtrack after that? What if it's a party and everyone is queueing their favourite song? The issue with recommendation engines is that they're dumb as rocks. They cannot tell that the Trentemoller remix might be related to War Pigs, but not Peppa Pig, without ears and a brain. So, to be safe, th…
What you are talking about (simple statistical aggregation) may be true 10 years ago. Deep learning is truly different. I'm not saying it is "smart" or listen the way we are. But is not "dumb" either in that it does not just follow prescribed rules. I personally prefer human curation. But I've heard many many stories of how spotify's AI sometimes surprises people with uncanny magical recommendations (and dumb ones to…
Deep learning is not smart nor is able to replace actual ears and understanding of music. Even a random recommendation system would be able to surprise once in a while.
Personally, I think Spotify's system is terrible and gives me a good suggestion every 100 wrong ones.
Earlier quoted context omitted.
I put the brakes on Libre.fm a little to avoid becoming a social silo. What’s there works and people keep using it. GNU social was a spin off, later merging with StatusNet and later Mastodon was a rewrite of GNU social in Rails.
Is libre.fm still stuck on PHP 5 or are the docs just out dated? https://git.savannah.gnu.org/cgit/librefm.git/tree/gnufm_ins...
I’m no longer involved with the GNU project so the site is in a weird state where the GNU docs are stuck in time. I do need to do a better job of pointing people to what’s out there though. I am considering a rewrite in modern PHP.
Last.fm (and the sadly defunct what.cd) have shaped my taste in music beyond what I could ever imagine: I have discovered a massive amount of amazing musicians through these recommendations; something I feel Spotify has never really been able to achieve, even after a decade+ of use. Scrobbling has almost become a religion to me, to the point I found solutions to scrobble my Vinyl listening and consider scrobbling cap…
I wanted to write exactly the same things you wrote, except I have only been on Spotify for 3 years now. I assume you use the Discogs app for scrobbling your vinyl? I was really pleasantly surprised when I found that feature :)
Earlier quoted context omitted.
What you are talking about (simple statistical aggregation) may be true 10 years ago. Deep learning is truly different. I'm not saying it is "smart" or listen the way we are. But is not "dumb" either in that it does not just follow prescribed rules. I personally prefer human curation. But I've heard many many stories of how spotify's AI sometimes surprises people with uncanny magical recommendations (and dumb ones to…
Deep learning is not statistical aggregation, but still wouldn't solve the very example OP and I are talking about. Deep learning is not smart nor is able to replace actual ears and understanding of music. Even a random recommendation system would be able to surprise once in a while. Personally, I think Spotify's system is terrible and gives me a good suggestion every 100 wrong ones.
True. And because there is no way to "measure" the quality, if you say it is now horrible your you, I'll take your word for it.
I don't believe in "General AI", But this is not a binary outcome. It WILL get better. How much? We'll see.
Contrary to popular belief Last.fm never really died (and I hope it never will), however it lost years ago its most valuable thing: *its own streaming service*. It was just perfect at everything, was it finding new releases, discovery obscure gems, or play your favorite things all over. It was so magical that you could hardly believe it was computer generated. Also, it was a wonderful "sane" social network where musi…
There is a place for both: Streaming services and DB/SN sites. they don't have to be the same.
I even hope for more segmentation (and interoperability) in the future: Companies that only provide the raw music. Others that build the UI/UX (players...) and still others that provides additional services (Social networking, Data related...)
Last.fm lost not because it is too genuine (CBS is one of the largest media conglomerates) but because it got lazy and failed to leverage its data to create more value. The truth is people are just as Lazy when it comes to music (organize, discover…), _so I wonder how much you can really grow in this space.
Earlier quoted context omitted.
> It's not that the algo is any worse than human recommendations, it's just that it's an average of all humans likes, which will never fit your exact personal unique preferences because they aren't you. Isn't that the definition of "worse"? "Never able to be tailored to your unique preferences" when a human could take that feedback in a single sentence and adjust? It's like the old "everyone wants to remake Excel sin…
I mean, maybe it's not worse though. Maybe others would find what the other guy wants too narrow. There's a tension between only playing stuff you are 100% going to like and actually introducing you to stuff you haven't listened to.
That's exactly what makes it worse, though. They currently have to choose more globally, it's not that personalized. in the human-curated world others would get different things. I know they don't like Slipknot, I know you do, I give you each different recommendations. Spotify's code hasn't shown the ability to learn "me" vs it's view of what the "average me" would like.
Contrary to popular belief Last.fm never really died (and I hope it never will), however it lost years ago its most valuable thing: *its own streaming service*. It was just perfect at everything, was it finding new releases, discovery obscure gems, or play your favorite things all over. It was so magical that you could hardly believe it was computer generated. Also, it was a wonderful "sane" social network where musi…
> it's sad it lost the streaming war pretty soon. There is a place for both: Streaming services and DB/SN sites. they don't have to be the same. I even hope for more segmentation (and interoperability) in the future: Companies that only provide the raw music. Others that build the UI/UX (players...) and still others that provides additional services (Social networking, Data related...) Last.fm lost not because it is…
Earlier quoted context omitted.
> it's sad it lost the streaming war pretty soon. There is a place for both: Streaming services and DB/SN sites. they don't have to be the same. I even hope for more segmentation (and interoperability) in the future: Companies that only provide the raw music. Others that build the UI/UX (players...) and still others that provides additional services (Social networking, Data related...) Last.fm lost not because it is…
Maybe related: https://news.ycombinator.com/item?id=29408761
> all the album by this label
label:[label name] is helpful. There are better options. this one comes to mind https://www.lbl.fm/
> all the songs produced by X
If you open the credits of a track, you will find that some writers (no producers) are hyperlinked to a page where you can listen to all their songs as a playlist.
> all the songs where in Y plays drums. All the albums recorded at some studio in the year
A Hint: try you luck with a search for a known label, producer or even drummer, or studio, and you will be surprised by how people are creative/meticulous with their public playlist’s choices (the human pool is just getting way too large, 400 millions and counting)
Also, you can take a look at https://spicetify.app/. It is a marketplace for extending the desktop app (some data related add-ins in there). it is still very young and hacky but IMO it is the right direction.