The hard part of AI coding is the second edit
Understand this story
Brian Woods writes on Hacker News that AI makes getting code running the first time cheaper, but subsequent edits easily introduce systemic degradation such as duplicate charges, and the real difficulty is maintaining invariants that must always hold. He proposes that each change answer four questions: specification, verification, provenance and authorization, and use Git, in-toto/SLSA, Sigstore and CI branch protection to string requirements, evidence and approvals into a traceable DAG, to prevent agents from certifying their own work as acceptable.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIThe Hard Part of AI Coding Is the Second Change
Brian Woods argues that AI agents make producing a working first change cheap, but accepting subsequent changes requires preserving what must stay true—such as no duplicate payments or cross-tenant data leaks—through specification, validation, provenance and authorization. He describes a synthetic experiment against Uncle's verifier where a signed record of a build with failed tests and audit returned VERIFIED, showing that attestation validity and release readiness are separate questions. He proposes a design in which each accepted change is attested by a trusted workflow, linked to prior attestations in a DAG, and verified by walking the graph, while noting the approach cannot prove tests were sufficient or the software correct.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 13 01:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.