[danielkuntz]

Not any good ones unfortunately! Great opportunity for someone to make one while other platforms are still scrapeable.

[leoh]

You don’t need to scrape other platforms. LLMs are already probably pretty darn good at this.

[m3kw9]

Music recommendations is a fools errand, I’ve never experienced or heard of a system consistently recommending it well. From my experience it’s 50:50, when it’s good it’s good then half the other time it’s Ed Sheeran

[echoangle]

Can LLMs analyze song features (danceability, instrumentalness, speechiness, tempo)?

[CamperBob2]

Audio analysis is one of the easiest problems that ML can deal with. The problem is, how can you use a pretrained LLM for discovering newly-released music? And how do you train future models without a source of new data?

[echoangle]

> Audio analysis is one of the easiest problems that ML can deal with.

Maybe, but that doesn’t tell me anything about LLMs. I’m not saying that it’s a particularly hard problem, I’m surprised that an LLM specifically would be good for this purpose.

[CamperBob2]

Yeah, there seems to be an unfortunate trend towards using "LLM" when people really mean "transformer."