AI & ML
Before you ship an LLM feature, build an eval set
LLM features fail in ways unit tests don't catch. A few dozen labeled examples and a repeatable scoring script turn "it seems fine" into evidence.
Senior Editor
Covers infrastructure, deployment and the business of developer tools. Previously a platform engineer.
LLM features fail in ways unit tests don't catch. A few dozen labeled examples and a repeatable scoring script turn "it seems fine" into evidence.
Understanding how your tools are funded helps you predict their future. A field guide to the common business models behind developer products.