"TODO: Fix the Mess Gemini Created": Towards Understanding GenAI-Induced Self-Admitted Technical Debt
Abstract
Analysis of AI-referencing code comments reveals that developers explicitly acknowledge technical debt in AI-assisted code, identifying patterns of postponed testing, incomplete adaptation, and limited understanding as key factors in AI-induced technical debt emergence.
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.
Community
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.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Self-Admitted Technical Debt in LLM Software: An Empirical Comparison with ML and Non-ML Software (2026)
- Vibe Coding in Practice: Flow, Technical Debt, and Guidelines for Sustainable Use (2025)
- An Empirical Study of Developer-Provided Context for AI Coding Assistants in Open-Source Projects (2025)
- AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents (2025)
- Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineering (2025)
- Quantitative Analysis of Technical Debt and Pattern Violation in Large Language Model Architectures (2025)
- Exploring Scientific Debt: Harnessing AI for SATD Identification in Scientific Software (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper