• LLM-as-judge — Using one model to score another's output against a rubric, so quality can be measured at a scale human grading cannot reach.
• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
• grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.

It's a concrete framework for judging whether AI-generated code is quietly rotting a codebase, going beyond correctness checks to metrics grounded in review and LOC growth, which matters as agents ship increasingly large diffs.

• articleConceptual integrity and counting lines of codesimonwillison.net
• videoGuide, Verify, Solve — Anirban Chatterjee, SonarAI Engineer
• videoStop Reading Every Line of CodeTheo - t3․gg

Checking sign-in…

Loading comments…