This one’s shorter than usual — less narrative, more a list I wish someone had handed me before I started running inference on Moya. If you’re about to do the same thing on your own cluster, save yourself the weekends I lost. 1. Your GPU desktop is now a pet, not cattle Kubernetes culture tells … Read more
Last post I covered the why behind running private AI on Moya. This one is the how — specifically, getting GPU-backed inference working cleanly on a bare-metal Kubernetes cluster instead of just running a model on a desktop with a script and calling it a day. If you’ve only ever run AI workloads on cloud-managed … Read more
When I teased “private AI workloads on Moya” in my first post, a few people asked me the same question: why bother? Cloud AI is one API call away, it’s cheap, and somebody else deals with the GPUs catching fire. Fair question. Here’s my honest answer, plus what’s actually running. The “How Does That Work?” … Read more
Last post covered why homelabs and Kubernetes specifically seem to be such a good (or dangerous) match for ADHD-style novelty-seeking and hyperfocus. This one is more practical: what the research and the ADHD community actually suggest for working with that pattern, mapped onto homelab and Kubernetes work specifically. None of this requires a diagnosis to … Read more
I’ve never met a homelab that was “done.” Mine certainly isn’t — Moya gets a new workload, Talyn gets torn down and rebuilt to test an idea, Pilot’s storage layout gets reorganized for the third time this year because I read one blog post about ZFS pool topology and suddenly the old layout looked wrong. … Read more
If you are anything like me, you cannot look at a perfectly functioning piece of technology—or a solid kitchen wall—without immediately thinking: “How does that work?” That foundational itch to tear things down, figure them out, and re-engineer them is exactly why I built StagNode. My family tells me my spirit animal is a stag, … Read more
