Revert rates show minimal difference between human and agent PRs

Tracking revert rates as a proxy for bad pull requests found one agent reverted about one per thousand, another 3.5 per thousand, and humans around 2.5 per thousand. There doesn't seem to be a very big difference between the rate at which pull requests were reverted from people versus agents in the study.

Daksh Gupta·Publié 27 sept. 2026

Derrière ce point de vue

Les traductions sont destinées à la lecture ; les extraits originaux restent la source evidence.

AI-Generated Code Is Already Competing With Human Code — Daksh Gupta, Greptile

Extrait original

Codex PR is reverted about one out of every thousand poll requests. Devon once every three and a half times every thousand poll requests. Humans right in the middle at about two and a half. So there doesn't seem to be very big difference between the rate at which poll requests were reverted from people versus agents in my study.

Cet extrait ne contient pas de contexte supplémentaire. Consultez la conversation originale.

Ouvrir l’original · 5:55 Voir la page source

L’heure de début provient de la transcription fournie. L’alignement avec la lecture est en attente de révision.