Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code Comments
For software engineering researchers and practitioners, this provides empirical evidence of how AI tools are actually used and adapted in real-world development workflows, revealing a shift from direct code generation to collaborative support.
This study analyzes 35,361 GitHub code comments referencing AI use and 12,996 subsequent commits to characterize how developers use AI tools in real projects. Results show AI is primarily used for code implementation, followed by enhancement, debugging, documentation, and testing, with subsequent commits involving refactoring and bug fixes, indicating sustained human oversight.
Developers increasingly use AI tools such as ChatGPT, Copilot, and Claude in everyday software workflows, but prior studies often evaluate LLM outputs in isolation rather than examining how developers adapt them in real projects. We analyze 35,361 GitHub code comments that explicitly reference AI use and their associated code blocks. We first open-code 500 unique comments and code blocks to derive a taxonomy of AI-assisted development activities, then annotate the full dataset using two LLM-based classifiers and aggregate predictions with Dawid-Skene expectation-maximization. We also analyze 12,996 subsequent commit messages to study how AI-assisted code evolves after introduction, and examine temporal trends from December 2022 to March 2026. Our results show that developers primarily use LLMs for code implementation, followed by code enhancement, debugging, documentation, and testing. Subsequent commits frequently involve refactoring and cleanup, feature integration and extension, and bug fixing, indicating sustained human oversight in adapting AI-assisted code. Over time, AI-referencing comments shift from direct code generation toward knowledge and conceptual support and code enhancement. These findings suggest that AI tools are becoming embedded not only as code-generation aids, but also as collaborative support mechanisms whose outputs are refined, extended, and corrected by developers over time.