Tag: ai
-
The Detector Was Never Looking
A neural network running at 5.8 milliseconds an inference, pointed at a room with cats in it, that had never once detected a cat.
I have an NVR. It runs in a container on one of the cluster nodes, it does object detection on that node’s integrated GPU, and it is fast: 5.84 milliseconds per inference, sitting at about 6% of what the detector can do. Person events come in with confidence scores between 0.73 and 0.93, which is healthy.
-
My Perspective on Digital Marketing and AI
Your stack isn’t short of AI. It’s short of tools that talk to each other.
Count the tools your Digital Marketing team opened this week. An SEO tool. A social listening platform. Two analytics platforms, because someone (me) standardised twice. A CMS. A design tool. A DAM. A translation service. A social publishing tool. A survey platform nobody’s looked at since the last wave closed.
-
Two Brains for My AI: How Obsidian and Trilium Split the Work
I've spent the last few months tinkering with a local AI stack on my desktop — Ollama for local inference, Hermes orchestrating the whole thing, and a Claude subscription for the heavy lifting. It works. But there was always one nagging gap I kept dancing around: where does the AI's memory actually live? For a…
Read more about Two Brains for My AI: How Obsidian and Trilium Split the Work