Teaching Six Security Cameras to Birdwatch

I have six UniFi cameras around the house, and every one of them has a microphone I had never once used for anything. Meanwhile there's a garden full of birds I can't identify and, if the flattened lawn is anything to go by, a nightly hedgehog

I Just Wanted Turn-by-Turn on My Wahoo (So Naturally I Built an Entire Route Planner)

I've been planning routes in one of the big commercial cycling apps for years - drag the line down the quiet lane instead of the A-road, sync to the Wahoo ELEMNT, ride. It's a good product. It is also somebody else's server holding every

Colour Me Impressed: Building an AI Colouring Book Factory in an Afternoon

My nine-year-old has been asking for colouring books. Not any particular colouring book, mind you - a steady stream of them, on whatever theme is occupying her brain that week. Dinosaurs one week, space the next. And every time, the options are the same: buy another one, or ask

The Charger, the Car, and the API That Wasn't There

My Ohme wall charger has lived its whole life on my wife's phone. Every time I wanted to know if the car was charging, or wanted to flip it to max charge before a long trip, the answer was "ask her phone". Tonight I fixed that,

Three Lies My LLM Stack Told Me

It started with an innocent question: "is there anything we can improve?" Two days later I'd benchmarked eleven model-and-runtime combinations, deleted over 150 GB of dead weights, patched an inference server to load a model format that doesn't officially exist yet, and

I Just Wanted It Louder (So Naturally I Lost All Sound First)

It started, as these things always do, with "the speakers are too quiet." The Legion Go 2 has a gorgeous OLED, a quick little Ryzen Z2 Extreme, and speakers that sound like they are apologising for existing. Even pinned at 100% they are polite to a fault. So

The Need for Speculative Speed

Chasing faster local LLM inference on Apple Silicon — the wins, one spectacular near-miss, and the bug I almost walked away from. There's a specific impatience that only shows up once you run language models locally. The cloud spoils you rotten, then you pull everything in-house and

The Brain in the Other Room

Or: how I stopped letting a laptop sleep on the embedding job. The previous setup ran a self-hosted RAG stack on a laptop. Open WebUI in Docker, Chroma for vectors, Tika for extraction, Infinity for embeddings, and an LLM running on the same box via the local server. It

My Patching Dashboard Grew a Brain (And Now It Checks Its Own Homework)

A while back I wrote about teaching my servers to reboot themselves. That post ended with a little FastAPI thing I'd built on top of the Ansible playbooks — host inventory, a terminal overlay streaming output over SSE, some big buttons labelled UPDATE and REBOOT. I called it Herdmon.

The Incident Was Coming From Inside The House

Or: the day a cluster tried to heal itself to death. The Silence It started with Plex. Then Paperless. Then Pocket ID. Uptime Kuma started quietly lighting up like a Christmas tree. Services on one node had stopped answering, but the node itself was... fine? A ping to one of

The Layer 3 Switch That Ate My Firewall

It started, as these things always do, with "I can't get to Karakeep." Not a server crash. Not a disk failure. Not even a misconfigured reverse proxy. Just a bookmark manager that worked yesterday and didn't work today. The kind of problem that should

96% (And It Only Took Seven Blog Posts to Get Here)

The last post ended with the model scoring 80% and confidently telling me that Plex -- the service running on my primary Proxmox node, mentioned hundreds of times in the training data -- does not exist. It was the best score yet and also the most embarrassing failure. Like acing an exam