AI Coding's Hard Part: The Second Change
Start here
Brian Woods argues that AI coding agents make a first working change cheap, but the second change is where systems break. In his example, an agent adding retries to a payment service can double-charge customers even while tests pass. He proposes requiring four answers before accepting a change — specification, validation, provenance and authorization — with agents proposing changes while independent workflows produce evidence and humans approve. Woods also shows that a signed attestation of a build with failing tests can return VERIFIED, since authenticity is not release readiness.
Generated from reports · updated 10 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIThe Hard Part of AI Coding Is the Second Change
Brian Woods argues that AI coding agents make a first working change cheap, but the second change is where systems break — an agent adding retries to a payment service can double-charge customers even while tests pass. He proposes requiring four answers before accepting a change: specification, validation, provenance and authorization, with agents proposing changes while independent workflows produce evidence and humans approve. He also shows a signed attestation of a build with failing tests can return VERIFIED, since authenticity is not release readiness.
Heat for this event
Not enough continuous observations yet to draw a trend.