hal

Posted by | October 22, 2026
LIVE DEMO: My Media Hub

I watch a lot of movies and shows, and I write about most of them. For years that meant juggling pieces that never quite talked to each other: a WordPress...

Continue Reading
Posted by | October 21, 2026
LIVE DEMO: Adding a Voice Agent to a “Second Brain” RAG Pipeline (and Megatron!)

Teaching the Second Brain to Listen and Talk Back A voice layer on top of the RAG pipeline — and why that's most of the way to a real voice...

Continue Reading
Posted by | September 30, 2026
The Anatomy of a Modern RAG Pipeline

Everything that sits between "we have a pile of documents" and "a person gets a trustworthy answer" This is another in the long line of "things Adam has made but...

Continue Reading
Posted by | September 27, 2026
Hardening a RAG Pipeline

Hardening a Personal RAG Pipeline: Redaction, Prompt Injection, and Knowing When It Actually Works I demonstrate how to build a retrieval-augmented question-answering system over my own notes — and the...

Continue Reading
Posted by | September 25, 2026
My Home Brain Learned to Talk Back: Adding RAG to Obsidian

Building a local RAG pipeline over my Obsidian vault, and why keyword search almost didn't work In my last post I described my "home brain": an Obsidian vault that my...

Continue Reading
Posted by | September 25, 2026
My Home Now Has a Brain (Obsidian)

How a folder of plain text files became the place where my home, my servers, my automations and my AI tools all meet Most mornings, the first thing I check...

Continue Reading
Posted by | July 27, 2026
PeeWee Termin’s Architecture

Pee Wee Termin is a 3D-printed T-800 skull with a Raspberry Pi in its chest, a GPU server as its cortex, and a rotating cast of personalities: a cranky teenager,...

Continue Reading