Kamal Reader

Product, test, data, or environment — and the evidence that tells them apart. TL;DR — A failing test tells you something broke, not what. I wrote a rulebook that sorts failures by one question: which artifact is wrong — the product, the test, the data it used, or the environment? Two LLMs applied it to 21 … Read more

Why 90% of Hot Storage Is Dead Weight (and How Modern Archiving Fixes It) There is an unspoken rule etched into every storage engineer’s whiteboard, sometimes called the Fundamental Theorem of System Administration: Users will always consume capacity faster than you can rack and provision raw disk. And its ruthless corollary: Every byte ever written … Read more

Most defenses against prompt injection are built around one question: does this text look malicious? I spent a weekend betting that’s the wrong question — and built a small tool that never reads the attacker’s words at all. It caught attacks the “smart” detectors missed. It also, with total confidence, blocked every single legitimate action … Read more

VRS, the Value Resolution System, grew out of DAS, an Unreal Engine plugin for abilities and effects in the spirit of Unreal’s Gameplay Ability System (GAS). While developing DAS and building parkour gameplay on top of it, I encountered a separate problem: managing abilities and effects was not enough; I also needed to coordinate changes … Read more

I began with a simple thesis: For decisions, accuracy matters more than speed. JEV is fast because it constrains a task to a bounded decision contract. I assumed that frontier LLMs would be more accurate, and that their extra latency would be an obvious trade worth making. So I built a reproducible benchmark to test … Read more