My Projects
-
Building a Private, Local, Zero-Cost, Transcription System on macOS Using AI
How a local macOS transcription pipeline became durable infrastructure by replacing fragile Python ML tooling with native Metal, keeping audio private, and removing subscription costs.
-
From SSH Friction to a Private LLM Cloud: Building a Private, Repeatable Ollama + EC2 Setup
Setting up a private, cloud-powered LLM environment on AWS sounds straightforward, until you actually do it. What started as a simple goal… “run Agent Zero with Ollama on EC2 without exposing sensitive data” …quickly turned into a maze of SSH quirks, Docker inconsistencies, networking gotchas, and AWS nuances. The good news: once you get through…