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·Published Sep 27, 2026

Behind the viewpoint

Translations are for reading; original excerpts remain the evidence.

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

Original excerpt

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.

Additional context is not included in this excerpt. Read the original conversation.

Open original · 5:55 View source page

Start time comes from the supplied transcript. Playback alignment is awaiting review.