“The average AI-generated pull request has 10.83 issues compared with 6.45 for human code, report claims.”

“Besides having 1.7x more issues on general, AI-generated pull requests also had 1.4x more critical issues and 1.7x more major issues, so they’re not just minor niggles.”

“The tech also introduced 1.76x fewer spelling errors and 1.32x fewer testability issues.”

I don’t think they actually linked to the source report, which is here: https://www.coderabbit.ai/blog/state-of-ai-vs-human-code-generation-report