Sentry CEO: AI Code Verification Is About Design Correctness, Not Compilation
trq212 · x · 2026-11-04
In a reply to trq212, Sentry CEO David Cramer argues that if you define verification as "does it compile," agents can handle it — but most verification for him is "is the design correct," which still needs human judgment.
Related event: Sentry CEO: AI Can Verify Compilation, But Humans Must Steer Design(2 posts)→
More from coding & agent
- Compound Engineering 3.35 encodes repo learnings as tests and lint rules, not just docs — kieranklaassen · 2026-11-04
- A nightly wiki-builder agent: prompt included, built for biotech tacit knowledge — nlarusstone · 2026-11-04
- Put static secrets in your HTTP proxy: exe.dev on agent-era key management — davidcrawshaw · 2026-11-04
- Claude to auto-connect plugins that trust it as an issuer, cutting agent re-auth friction — testingcatalog · 2026-11-04
- Dev used Claude to fix one bug across many repos — some rejected PRs just for AI-written code — cneuralnetwork · 2026-11-04
- Dev admits signup-bot agents "went off the rails," blames AI, and X piles on — evilsocket · 2026-11-04