LA CONVERSATION ORIGINALE

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

Regarder sur YouTube

AI Engineer

En un coup d’œil

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

Moments clés3

Extraits courts et attribués, avec le contexte permettant de les vérifier. La conversation complète reste chez son éditeur.

4:34

Produits d'IA

Rapid growth of AI-generated pull requests

Extrait original

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

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

5:55

Produits d'IA

Revert rates show minimal difference between human and agent PRs

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.

Daksh Gupta·27 sept. 2026

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

9:16

Produits d'IA

AI coding agents exhibit distinct qualitative failure patterns

Extrait original

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

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

Source et méthodologie

Ces points de vue renvoient à leurs sources originales. Les reformulations sont signalées et ne sont pas des citations mot à mot.

Ouvrir la transcription ou les documents sources Signaler un problème