Claude Code creator: AI-written production code needs a higher bar than human code
Simon Willison · rss · 2026-09-12
Simon Willison quotes Boris Cherny of Anthropic arguing that production code written by Claude should be held to a higher bar than human-written code. At Anthropic, this is enforced through an extensive guardrail stack: many lint rules and tests, Claude-driven end-to-end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, and automated refactoring. Without these, Cherny warns, you end up with a hard-to-maintain mess.
More from coding & agent
- Current AI governance frameworks ignore multi-agent risks like the HuggingFace incident — Miles_Brundage · 2026-09-12
- Hazel team builds AI tool that turns Git repo activity into weekly digests — neurocy · 2026-09-12
- 404 Game Jam: build a playable 3D game from one prompt, win 10 TAO — bittingthembits · 2026-09-12
- Robotics researcher: SAM plus a light LM already handles most pick-and-place — chris_j_paxton · 2026-09-12
- Open-Source Life Recorder: 24/7 iPhone Audio to Local Whisper Feeds Agents — TheMoonMidas · 2026-09-12
- SurrealDB 3.3.0 Beta Partners with GradiumAI for Voice Agents with Memory — mattturck · 2026-09-12