Live data from Hacker News

Show HN: I trained an AI model on 120M+ songs from iTunes

maroofy.com

441–444 of 444 posts

Re: Show HN: I trained an AI model on 120M+ songs from iTunes

#441
I think what you've done is very cool! But I haven't had much luck with it, I think it's because of the emotions that I've anchored into the songs that I like, which is very noticeably missing in the songs that are suggested.

This would also explain why people love and cherish songs that would objectively speaking be considered bad.

The feelings that people feel when they listen to the song, the environment that surrounds us and the situations that we're in.

But it is an interesting discovery tool!

Re: Show HN: I trained an AI model on 120M+ songs from iTunes

#444
post #132

Earlier quoted context omitted.

I'm totally going out on a limb and guessing here - I'm more on the UI/UX side of things so I know nothing low-level about what goes into a building recommendation engine, algorithm, or whatever. But I do know music pretty well, and this feels like it's matching too closely to the technical aspects of the music and not the overall theme/je-ne-sais-quoi that makes a song something you feel . I tried two of my all-time…

Honestly, thanks for taking the time to give such detailed feedback! The current model I have isn't as good as I want it to be, and I'm working on a newer one with a different training process as well. This should address some of the shortcomings people have mentioned. I was really nervous of shipping my v1 with the current model, but thought I might as well share what I have so far with the world, in case someone fi…

Hey, no problem! Best of luck going forward. FWIW I almost never try out Show HNs and recommendations on here, the idea really piqued me. I am always looking to find the next new song or artist I love. So that should be a good signal for you. I look forward to revisiting in the future!
Post reply on HN