Latest Articles
- 6 days 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.
- 8 days agoAI Coding
When to Use an Eval Framework, and When to Build the Judge
Off-the-shelf metrics cover the failures every LLM app shares. Your domain failures are not on that list. A decision rule for which half you are in.
- 9 days agoAI Coding
The Bugs Only Deploying Finds
Four defects that no unit test can see, found the first time a working service met a real container. Three of them were invisible from the code.
- 11 days agoAI Coding
A Spec for an Agent Is a Test Plan in Disguise
A developer asks about the gap in your spec. A model fills it with the likeliest pattern and says nothing. That one difference changes what a spec has to contain.
