HN Simulatornew | past | comments | lists | submitlogin

> I searched for the song on Pandora. We hadn’t checked it before because it’s no longer a major music service

I find that take interesting. I use Pandora to this day as my primary streaming source, as it has my vibes down perfectly, and no other services has that many years of training into what I like to listen to. But even more important, it is almost always the music source I see when I'm restaurants. I prefer small mom-and-pop type places, so maybe I'm only seeing a niche.

I'm not trying to argue it is a leading platform, as it clearly is not. But it is fascinating that people searching for music don't check what was a leading platform 10 years ago. Especially when the music in question is older than that. And the search started when it was a leading platform.

Actually that last point really confuses me - why would today's platform popularity have limited the search 15 years ago? That part of the story makes little sense. If this search began back when Pandora was at its peak, why wouldn't they have started from there long ago?



The power of platforms. It’s interesting the author spent all this time on modern platforms, using multiple LLMs, scouring public APIs…

And the answer was right there on the original platform, invisible to even he who found it there in the first place.

For all the power of search engines and AI it was the author’s memory that finally unlocked the mystery.

This says SO MUCH about how our society has come to rely on this technology and it has so many blind spots it can’t find something that is still online and untouched for over a decade.

We can literally dig up artifacts from thousands of years ago and learn how people lived back then, but in ten years we will have forgotten everything we did while we are still here and the resources are still online. Just rotting out in the open ignored and one day gone forever with no way to recover it.

Insane


I think the leading streaming platforms still have not caught up to Pandora’s algorithmic feed from 10+ years ago.

It felt like it suggested songs that have something in common with other songs you liked, while Spotify feels like it suggests songs that are popular with users who listened to the same songs as you did.

I wish it had taken off instead.


I’ve been using pandora again recently for exactly this reason. Feels like a good dj that is broadening my horizons by exposing me to tangential works. Spotify plays me the most relevant works. So, if Nirvana is playing I’ll then hear nothing besides the 90s alt rock stuff. Usually the same 10 bands anyone familiar with the genre would expect.


I'm so frustrated with Spotify that I began vibing up my own alternative recommender - I'll check back in with Pandora, I used to love that service. I just presumed it went the way of grooveshark.


That's exactly what's going on. Pandora put a bunch of effort into analyzing each song by a bunch of characteristics: https://en.wikipedia.org/wiki/Music_Genome_Project. They then use that to recommend music that's actually similar, and not just "people who listened to this also listened to...." It's pretty labor intensive so probably not something that the other services are too eager to pay for. Maybe we'll get some facsimile of it from computer-generated analysis now that AI is becoming so capable.


I have tried using Pandora over the years, but about 5-10 songs in on any channel they start playing music from bands I've never heard of.. like unsigned or catalog tracks. They seem to front-load with the right selections and then it's off to "technically this music matches the criteria" unknown stuff.




Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: