MB

▄▄▄·▪ ▐ ▄ ▄▄▄ . ▐█ ▄███ •█▌▐█▀▄.▀· ██▀·▐█·▐█▐▐▌▐▀▀▪▄ ▐█▪·•▐█▌██▐█▌▐█▄▄▌ .▀ ▀▀▀▀▀ █▪ ▀▀▀

I have given Claude Code a try for a couple of months now. For my personal projects, it at first sounded fun being able to create all my ideas that I have easily and fast (and without needing to write frontend JavaScript). But in my experience it is not much different from AI Art (drawing, paintings, etc). It feels fun at first but you don’t get the satisfaction of creating something. I don’t need to create these projects, so why bother rushing things. The joy of programming itself is to me worth much more than the result or using my projects. I will still use AI, but not for anything like a new feature or entire parts of the code, maybe a function here and there. But for reviewing and debugging it is useful to me.

I am also looking into running these kinds of things locally, in the following months I should get some new hardware for this.

Got done setting up AudioMuse-AI on my bare metal k8s cluster. For those who don’t know what AudioMuse-AI is, it is a sonic analysis tool with a web interface that can hook into your Navidrome library. This is something I have played around before and always was planning to create myself. But the community beat me to it, more time for other projects I guess. Analysis of my almost 200GB music library took about 12 hours. It was a nice workload for my cluster to show me what it got. It’s a workload that scales perfectly horizontally, it can consume any compute that you can throw at it. On my old NAS it would take days, if not a week.

Below is my current music map: a 2D projection of the track vector space color-coded by genre. TLDR, closer songs sound more simular.

audiomuse-ai music map