Archive
Rantings of an old geek.
Index
9 entriesIn August Anthropic said they will put invisible watermarks in text written by Claude, a hidden pattern that only their own tools can detect. In October OpenAI said the same for the EU. So the labs want to know which text came from their models. My first thought was, OK, can we do the opposite? Send some requests to an API, look at what comes back, and know which model is behind it.
Bring your own GPU · Part 3
vLLM takes 90% of each GPU before anyone connects. Working out where it goes gave me a limit on requests in flight, and the proxy in front of vLLM now enforces it.
A personal setup that researches one article from my filtered feed and turns it into audio for my commute.
Bring your own GPU · Part 2
My first benchmark said two RTX 3090s were 21 times slower per token than one. A rerun looked fine, and I had changed too many things to know why. That changed how I test.
We're coding with AI now. The old concepts assumed the author and the reader are the same person. They're not anymore.
Bring your own GPU · Part 1
nvidia-smi showed my 3090 at 100% while my agents got slower. Timing prefill and decode separately showed a card that was mostly waiting on memory.
A look at AI botnets, insecure devices, DDoS risk, and who needs to fix the mess.
Automation, AI, cloud, and the jobs most exposed to software and machines.