~40,000 passing tests: dev explains why he doesn't review every line of AI code

doodlestein · x · 2026-09-19

Responding to skeptics who ask how he knows AI-written code works without manual line-by-line review, doodlestein points to a suite of 40,000 tests that just passed — not trivial mocked unit tests, but every kind of test including heavy e2e integration coverage — as his verification strategy for agent-generated code.

Original post →

More from coding & agent

coding & agent channel →