~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.
More from coding & agent
- Dev builds Chrome extension with Jev to auto-tag sites and visualize browsing habits — pramodk73 · 2026-09-19
- One prompt, under $1: coding agent builds a full Django to-do app in 5 minutes — Al_Grigor · 2026-09-19
- One Generic Video Tool or Per-Provider Tools? Debating the Agent Tool Layer — ExcitingBison4616 · 2026-09-19
- Readback: free MIT VS Code extension reads Claude Code replies aloud via Speechify — shauntrennery · 2026-09-19
- GitHub Next open-sources LocalJev, a local Jev-compatible API built on oMLX and DiffusionGemma — gaganghotra_ · 2026-09-19
- WebMCP benchmark: Jev + Mercury 2.5 solves 100% of tasks at 112x lower cost than GPT-6 Astra — hardimanjames · 2026-09-19