Your evaluation set has an expiration date. Last month it helped you pick a model. This month it is...
Your Eval Set Is Rotting: A Theme-Fingerprint Drift Check
Related
The three files an Angular monorepo needs before an agent writes a line
One file the agent must read, one it must pass, one it must stay inside. An afternoon of work, and the oversized diff fails before review.
Prompt Pad: What Are Tokens?
Your AI doesn't read your prompt word for word. It reads tokens. In this episode of Prompt Pad,...
I measured what my Claude Code setup costs on every request. Most of my skills had gone blank.
Claude Code sent 74,500 tokens with my first message of the day, before it had read a single word I...