4 posts on LLM.
Two projects both named Atomix. One a Python pipeline that turns a biography into a documentary. One a monorepo shell hosting four render apps.
A workshop curriculum built around the failure modes I hit in production, not the demos in a keynote. What I taught, what worked, and where the syllabus fell over.
I gave my phone number to an AI. Gemini Live speech-to-speech didn't survive reality. Here is the three-stage pipeline I fell back to, and how it hides 700ms.
My phone number is on the internet and an LLM answers it. Six months in, the guard-rails that actually mattered, and the one rule I had to soften mid-flight.
