Accuracy over Speed: Experimenting with a Two-Pass AI Pipeline for Local LLMs
How I tested whether server-local AI could handle financial document extraction well enough to avoid relying on a large hosted model API.
Read more →Passionate Full Stack Developer | Platform & Infrastructure Enthusiast
All blog posts related to infrastructure
How I tested whether server-local AI could handle financial document extraction well enough to avoid relying on a large hosted model API.
Read more →What I learned turning a homelab budgeting tool into my first paid SaaS, and why the post itself got delayed.
Read more →Adding a Virtual IP to Talos Kubernetes for resilient control plane access
Read more →