Vibeleaderboard
← All Intel
Intel / article

Quoting Boris Cherny

Source
simonwillison.net
Date

Context

Boris Cherny argues that production code generated by Claude needs a higher acceptance standard than human-written code. In his quoted statement, he describes Anthropic using automated testing, code review and security review to enforce that standard. His concern is maintainability: generating a working change can still leave a codebase harder to manage. The account presents those checks as part of the work required to use coding agents responsibly, without claiming a measured reduction in defects.

Terms in this piece · Glossary
  • guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Read the source simonwillison.net
Recommended reads
Comments

Checking sign-in…

Loading comments…