Stats

5
Posts
5
Experiments
2
WILTs
10,404
Words Written
24
Total Views

Top Topics

agents (2)

Recent Content

postQuill Passed Its Detection Bar With 40 Features and No LLM
WILTA diff review is a verification layer the tests don't cover
experimentThe CRAP Loop: Driving 334 Risk Hotspots to Zero in a Day
postThe 13 Behavior Drifts a 2,500-Test Suite Missed
experimentQuill: Was the Human Reference Just Too Old?
experimentQuill: Diagnosing a Critic That Scored Humans as More AI Than AI
experimentQuill: A Critic That Can Detect AI but Can't Rank It
experimentTwo Small Routers for an LLM Gateway, and Why Neither Shipped
WILTExternalize what you want remembered
postI Had AI Agents Audit How I Work With AI Agents