LA CONVERSACIÓN ORIGINAL

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

Ver en YouTube

AI Engineer

De un vistazo

Rapid growth of AI-generated pull requests[1]Ver el momento de apoyo
Revert rates show minimal difference between human and agent PRs[2]Ver el momento de apoyo
AI coding agents exhibit distinct qualitative failure patterns[3]Ver el momento de apoyo

Momentos clave3

Fragmentos breves y atribuidos, con el contexto necesario para verificarlos. La conversación completa permanece con su editor.

4:34

Productos de IA

Rapid growth of AI-generated pull requests

Extracto 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

Este fragmento no incluye más contexto. Consulta la conversación original.

5:55

Productos de IA

Revert rates show minimal difference between human and agent PRs

Extracto 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

Este fragmento no incluye más contexto. Consulta la conversación original.

9:16

Productos de IA

AI coding agents exhibit distinct qualitative failure patterns

Extracto 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

Este fragmento no incluye más contexto. Consulta la conversación original.

Fuente y metodología

Estas perspectivas enlazan a sus fuentes originales. Las paráfrasis están identificadas y no son citas textuales.

Abrir transcripción o material de origen Reportar un problema