Posts
Newest first · Stack map →
Jul 20, 2026
Picking a local model with six tests instead of a hunch
The free model on my GPU box was unreliable in a way I could not name. Before swapping it, I found the reason by reading its transcripts, then ran a controlled A/B of six scored tests in an isolated copy of the real harness. The candidate won 5 to 2, a longer soak passed 21 of 22, and the swap was one line.
Jul 6, 2026
Running my own models so the routine work costs nothing
A lot of the small jobs I was paying a hosted model to do did not need a frontier model at all, so I started running open-weight models on my own GPU box and let the routine work run for free.