So, I decided to do a little experiment. With Opus 5 just launched, I set it loose on a pretty deep,...
I Burned My £20 Cursor Budget on Opus 5 (And All I Got Was 44 Files of Absolute Garbage)
Related
From Azure DevOps ticket to pull request: an agent skill that stops short of merge
An agent workflow that reads an Azure DevOps work item, guides a coding agent through implementation, validates the changes, and opens a PR — plus the false-green bug I found while...
I Had a Lot of Fun Building a Linux Packet Flight Recorder
I built skbx to follow packets through the Linux kernel, preserve what it observed, and replay the evidence later without root.
My Verification Gate Cleared on a Keyword, Not Evidence
A reader turned my sycophancy gate into an observable test, and the gate failed it — its escape condition was a keyword in the agent's own prose. I measured the false-positive cost...