More Like this

1. ChatDBG: Augmenting Debugging with Large Language Models

   https://doi.org/10.1145/3729355  

   Levin, Kyla H; van_Kempen, Nicolas; Berger, Emery D; Freund, Stephen N (June 2025, Proceedings of the ACM on Software Engineering)

   Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and user-friendliness of conventional debuggers. ChatDBG lets programmers engage in a collaborative dialogue with the debugger, allowing them to pose complex questions about program state, perform root cause analysis for crashes or assertion failures, and explore open-ended queries like why is x null?. To handle these queries, ChatDBG grants the LLM autonomy to take the wheel: it can act as an independent agent capable of querying and controlling the debugger to navigate through stacks and inspect program state. It then reports its findings and yields back control to the programmer. By leveraging the real-world knowledge embedded in LLMs, ChatDBG can diagnose issues identifiable only through the use of domain-specific reasoning. Our ChatDBG prototype integrates with standard debuggers including LLDB and GDB for native code and Pdb for Python. Our evaluation across a diverse set of code, including C/C++ code with known bugs and a suite of Python code including standalone scripts and Jupyter notebooks, demonstrates that ChatDBG can successfully analyze root causes, explain bugs, and generate accurate fixes for a wide range of real-world errors. For the Python programs, a single query led to an actionable bug fix 67% of the time; one additional follow-up query increased the success rate to 85%. ChatDBG has seen rapid uptake; it has already been downloaded more than 75,000 times. 

   more » « less
2. Non-Expert Programmers in the Generative AI Future

   https://doi.org/10.1145/3663384.3663393  

   Feldman, Molly Q; Anderson, Carolyn Jane (June 2024, ACM)

   Generative AI is rapidly transforming the practice of programming. At the same time, our understanding of who writes programs, for what purposes, and how they program, has been evolving. By facilitating natural-language-to-code interactions, large language models for code have the potential to open up programming work to a broader range of workers. While existing work finds productivity benefits for expert programmers, interactions with non-experts are less well-studied. In this paper, we consider the future of programming for non-experts through a controlled study of 67 non-programmers. Our study reveals multiple barriers to effective use of large language models of code for non-experts, including several aspects of technical communication. Comparing our results to a prior study of beginning programmers illuminates the ways in which a traditional introductory programming class does and does not equip students to effectively work with generative AI. Drawing on our empirical findings, we lay out a vision for how to empower non-expert programmers to leverage generative AI for a more equitable future of programming. 

   more » « less
3. What we eval in the shadows: a large-scale study of eval in R programs

   https://doi.org/10.1145/3485502  

   Goel, Aviral; Donat-Bouillud, Pierre; Křikava, Filip; Kirsch, Christoph_M; Vitek, Jan (October 2021, Proceedings of the ACM on Programming Languages)

   Most dynamic languages allow users to turn text into code using various functions, often named eval, with language-dependent semantics. The widespread use of these reflective functions hinders static analysis and prevents compilers from performing optimizations. This paper aims to provide a better sense of why programmers use eval. Understanding why eval is used in practice is key to finding ways to mitigate its negative impact. We have reasons to believe that reflective feature usage is language and application domain-specific; we focus on data science code written in R and compare our results to previous work that analyzed web programming in JavaScript. We analyze 49,296,059 calls to eval from 240,327 scripts extracted from 15,401 R packages. We find that eval is indeed in widespread use; R’s eval is more pervasive and arguably dangerous than what was previously reported for JavaScript. 

   more » « less
4. Explaining Social Recommendations Using Large Language Models

   https://doi.org/10.1007/978-3-031-66635-3_7  

   Ashaduzzaman, Md; Nguyen, Thi; Tsai, Chun-Hua (January 2024, Springer Nature Switzerland)

   This paper introduces an innovative approach to recommender systems through the development of an explainable architecture that leverages large language models (LLMs) and prompt engineering to provide natural language explanations. Traditional recommender systems often fall short in offering personalized, transparent explanations, particularly for users with varying levels of digital literacy. Focusing on the Advisor Recommender System, our proposed system integrates the conversational capabilities of modern AI to deliver clear, context-aware explanations for its recommendations. This research addresses key questions regarding the incorporation of LLMs into social recommender systems, the impact of natural language explanations on user perception, and the specific informational needs users prioritize in such interactions. A pilot study with 11 participants reveals insights into the system’s usability and the effectiveness of explanation clarity. Our study contributes to the broader human-AI interaction literature by outlining a novel system architecture, identifying user interaction patterns, and suggesting directions for future enhancements to improve decision-making processes in AI-driven recommendations. 

   more » « less
5. Evidence About Programmers for Programming Language Design (Dagstuhl Seminar 18061)

   https://doi.org/10.4230/DagRep.8.2.1  

   Stefik. A., Sharif (January 2018, Dagstuhl reports)

   The report documents the program and outcomes of Dagstuhl Seminar 18061 "Evidence About Programmers for Programming Language Design". The seminar brought together a diverse group of researchers from the fields of computer science education, programming languages, software engineering, human-computer interaction, and data science. At the seminar, participants discussed methods for designing and evaluating programming languages that take the needs of programmers directly into account. The seminar included foundational talks to introduce the breadth of perspectives that were represented among the participants; then, groups formed to develop research agendas for several subtopics, including novice programmers, cognitive load, language features, and love of programming languages. The seminar concluded with a discussion of the current SIGPLAN artifact evaluation mechanism and the need for evidence standards in empirical studies of programming languages. 

   more » « less