AI & ML
How to get real value from AI code review
AI reviewers are good at catching certain classes of bugs and terrible at others. Teams that benefit treat them as a first pass, not a gatekeeper.
Tag
#llm
Every story tagged #llm.
AI & ML
Give your AI coding assistant a project brief
Coding assistants start every session knowing nothing about your project. A short, well-maintained instructions file fixes most of the "it ignored our conventions" complaints.
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.