DAS URSPRÜNGLICHE GESPRÄCH

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

AI Engineer · 27. Sept. 2026 · 12:40

Daksh Gupta discusses AI-generated pull requests, how their revert rates compare with human-written changes, and differences in the types of errors coding agents produce.

Daksh Gupta

Auf YouTube ansehen

AI Engineer

Auf einen Blick

Rapid growth of AI-generated pull requests[1]Unterstützendes Moment lesen
Revert rates show minimal difference between human and agent PRs[2]Unterstützendes Moment lesen
AI coding agents exhibit distinct qualitative failure patterns[3]Unterstützendes Moment lesen

Schlüsselmomente3

Kurze, zitierte Textstellen mit Kontext zur Überprüfung. Das vollständige Gespräch bleibt beim Herausgeber.

4:34

KI-Produkte

Rapid growth of AI-generated pull requests

Originalauszug

And I came to the result that about a quarter of all the poll requests that Graal was reviewing in any given month were completely or at least largely generated by AI. Then I backtracked this data to the last 12 months and it turns out that this number is growing really fast. In fact, early last year, fewer than 1% of pull requests had any evidence of being completely AI generated.

Daksh Gupta·27. Sept. 2026

Dieser Auszug enthält keinen weiteren Kontext. Lesen Sie das Originalgespräch.

5:55

KI-Produkte

Revert rates show minimal difference between human and agent PRs

Originalauszug

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.

Daksh Gupta·27. Sept. 2026

Dieser Auszug enthält keinen weiteren Kontext. Lesen Sie das Originalgespräch.

9:16

KI-Produkte

AI coding agents exhibit distinct qualitative failure patterns

Originalauszug

Claude is one and a half times more likely to produce a SQL injection error than humans. Devon is about half as likely as humans to produce a off bypass issue. I found it very interesting that there was this much variation in how these agents were performing and how different their failure modes were from humans.

Daksh Gupta·27. Sept. 2026

Dieser Auszug enthält keinen weiteren Kontext. Lesen Sie das Originalgespräch.

Quelle & Methodik

Diese Standpunkte sind mit ihren Originalquellen verknüpft. Paraphrasen sind gekennzeichnet und keine wörtlichen Zitate.

Transkript oder Quellenmaterial öffnen Ein Problem melden