Hacker News Reader

This is super cool. Using LLMs to mix together two songs that don't belong mixed together is a great usecase.

It’s a method like any other. The process took him two days, after the LLM suggested which track to mix (like he was working for the LLM instead of the other way around?). Two days is more than enough to learn how to make a mashup in Ableton without LLM’s.

Seems though that working with those AI tools appeals to the author, that they learned and had fun, so I guess that makes it a good usecase for them specifically?

Author here, I think you’re spot on. If I set out specifically to make a mashup and spent the same number of hours working toward that goal I think I could have gotten to the same place. This was a journey that started with wrapping my head around MCP and LLM local software interoperability, and my Ableton knowledge leveled up a lot along the way.

I think this tooling could be useful in the hands of more capable musicians / audio engineers / etc. as there are often repetitive tasks in DAWs and it could potentially unlock new workflows that would have been too tedious without knowing how to program.

Reply on news.ycombinator.com