Notes
from the work
What I learned, decided or changed my mind about while building the projects and running the experiments.
-
AI Workflows
Training my first language model on a GTX 1650
A 4 GB GPU, a small corpus and a lot of things that went wrong in instructive ways. The story around AI.001, with a few examples of what the model actually produced. -
AI Workflows
Why most of my AI projects start local-first
For personal experimental systems I want the first working loop under my control. The cloud comes in after I understand what it's for. -
Systems
Why I built a tiny mission control for my homelab
Once a lab has enough independent parts, the question stops being whether a service runs and becomes what is happening across all of it, right now. -
Systems
My homelab doesn’t need Kubernetes
Kubernetes solves real problems. They just aren't the ones I have, and my lab is better off boring. -
AI Workflows
What does “memory” actually mean for a personal AI agent?
Storing every conversation is easy. Deciding what should still be believed, where it came from and when it should stop mattering is the hard part.
Keep exploring
The questions behind these notes
Each note starts from something I tested. The experiments hold the method, the evidence and what did not work.