~/tags $ grep -l '#adversarial-review' _posts/*
// #adversarial-review
3 posts tagged.
My Steering Rules Hid a Bug for Three Months, Then Found It in an Hour
A wrong sentence in my always-on Cline rules ('there is no LVM event autoactivation on this host') loaded into every session for three months and quietly capped how deep any diagnosis could go. The same harness then c...
Auditing a Homelab With AI Agents: Personas, Four Waves, and an Adversarial Verifier
The architecture of a security-review system built from AI agent personas: a read-only auditor with a hard constraint list, a four-wave pipeline where each wave answers a question the previous one cannot, a checklist ...
When the Output Looks Right: Why a Green Test Suite Stops You Looking
Anthropic's AI Fluency Index found that people get less critical exactly when an AI produces something polished: fact-checking drops 3.7 points and spotting missing context drops 5.2 points the moment code or document...