Review moved before the PR: Claude must prove completion with tests; Boris Cherny cites 2-3x quality gain
ccerrato147 · x · 2026-10-29
From Addy Osmani's thread: where did the review go? Before the pull request. Claude doesn't get to say it's done — it has to show it: run the tests and the build, match the screen to the design. Then a fresh, context-free agent reads the diff.
Boris Cherny, who built Claude Code, puts the quality gain at 2 to 3x.
Related event: How Anthropic reviews code when Claude writes 90% of it(6 posts)→
More from coding & agent
- Interface Lineage opens: 15 years of collected interfaces, 500+ patterns free to read — round · 2026-10-29
- GitHub lays out its agentic-era evolution at GitHub Universe, led by Jay Parikh — 0xkarasy · 2026-10-29
- Designer runs a daily bot to scout the web for design 'specimens' matching her taste — round · 2026-10-29
- Jason Kneen shares slop_eisley 0.6.22 roadmap for his AI-built FPS game — jasonkneen · 2026-10-29
- Free Oct 29 Every livestream: Context Engineering With DSPy, open to all — danshipper · 2026-10-29
- Open-source lead gen agent Jev at $0.0024/lead; blogger ran a job hunt for $0.13 — JaynitMakwana · 2026-10-29