Code created by AI requires more attention and contains worse errors

Generating code using AI increases the number of issues to be checked and the severity of those issues.

CodeRabbit, an AI-based code review platform, made this decision by examining 470 open source pull requests for its State of AI vs. Human Code Generation report.

The report finds that AI-generated code has significantly more flaws in logic, maintainability, security and performance than human-generated code.

On average, AI-generated pull requests (PRs) contain approximately 10.83 issues each, compared to 6.45 issues in human-generated PRs. That’s about 1.7x when AI is involved, meaning longer code reviews and increased risk of errors.