Latest Articles
- about 1 month agoDevOps
Your Pipeline Config Is Your Real Test Strategy
A framework says how tests are written. The pipeline says which failures stop a release, how fast confidence arrives, and what happens when it does not. Read yours.
- about 1 month agoAI Coding
The Detector That Always Finds It Is Not a Detector
A bias check that fires on every judge proves nothing. What it takes to make an agent evaluation say something — and the level that graded an answer it had never seen.
- about 2 months agoAI Coding
Subagent Configuration Is Least-Privilege Design
Every knob on a subagent answers the same question: what may this thing see and do? Read them that way and the defaults stop looking reasonable.
- about 2 months agoAI Coding
Your Streaming Benchmark Measures Two Things
Streaming cut time-to-first-audio from 1574 ms to 450 ms. Only one of those two mechanisms scales with input length, and conflating them makes the number useless.
