"TODO: Fix the Mess Gemini Created": Towards Understanding GenAI-Induced Self-Admitted Technical Debt
By: Abdullah Al Mujahid, Mia Mohammad Imran
As large language models (LLMs) such as ChatGPT, Copilot, Claude, and Gemini become integrated into software development workflows, developers increasingly leave traces of AI involvement in their code comments. Among these, some comments explicitly acknowledge both the use of generative AI and the presence of technical shortcomings. Analyzing 6,540 LLM-referencing code comments from public Python and JavaScript-based GitHub repositories (November 2022-July 2025), we identified 81 that also self-admit technical debt(SATD). Developers most often describe postponed testing, incomplete adaptation, and limited understanding of AI-generated code, suggesting that AI assistance affects both when and why technical debt emerges. We term GenAI-Induced Self-admitted Technical debt (GIST) as a proposed conceptual lens to describe recurring cases where developers incorporate AI-generated code while explicitly expressing uncertainty about its behavior or correctness.
Similar Papers
Self-Admitted GenAI Usage in Open-Source Software
Software Engineering
Shows how people use AI to write computer code.
The Impact of Generative AI on Code Expertise Models: An Exploratory Study
Software Engineering
Makes computer code knowledge checks less reliable.
Understanding Self-Admitted Technical Debt in Test Code: An Empirical Study
Software Engineering
Helps fix computer code faster and better.