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,
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 discovered that
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
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 watch a
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 worked.
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.
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
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
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
The last post ended with a cliffhanger: V8 was training, the dataset had been surgically rebuilt with 140 hand-written gold pairs, and the target was 76-82%. Three days, several explosions, and one strongly-worded email later, the model hit 80%. Ten points above V7. Best score yet. Getting there was the
The last post ended with a model that scored 46% and the profound insight that throwing more parameters at a problem is not, in fact, a substitute for having good training data. Revolutionary stuff. Nobel committee, you know where to find me. What followed was about 24 hours of increasingly
This is the boring sequel. The 9B model trained on the first attempt. No SSH failures, no disk full errors, no cascading tracebacks. The custom Docker container did its job. I launched the pod, it pulled the image, SSH connected, training started, and 50 minutes later I had a model.