This research paper describes an exploratory study on the effectiveness of Chat Debugging: troubleshooting malfunctioning analog circuits on breadboards and printed circuit boards (PCB) by undergraduates through conversations with public-domain large language models (LLMs). Through thematic analysis of students'voluntarily shared chat logs when debugging pre-determined buggy circuits under exam and time pressure, we discovered multimodal usage patterns by students and considerable domain knowledge and sensible debugging suggestions offered by off-the-shelf LLMs. Meanwhile, we also identified major gaps in LLM technologies and students'skills during human-AI collaborative debugging, such as LLMs'limitations in 2D/3D image-based reasoning, unjustified tone of confidence, and students'deficits in fundamental concepts and critical thinking.
Debugging is an immense challenge for novices when learning programming, often causing frustration. Applying a systematic debugging process has a considerable impact on debugging success. As a result, several interventions have been designed to teach this process to students. However, understanding how students actuall...
Elena Spörer, Tilman Michaeli· Proceedings of the 2026 Unit...· 1 citation
Generative artificial intelligence tools are increasingly embedded in student programming workflows. Students use these tools to generate, explain, modify, and refine code through natural-language interaction. This development raises important questions about understanding, verification, responsibility, and the educati...
Lovro Šantek, Filip Buljan, Maksim Madžar et al.· International Symposium ELMA...· 0 citations
An AI-assisted teaching model for microcontroller programming practice based on three functional modules, namely code-skeleton generation, compilation/logic-error diagnosis, and personalized question answering is built and preliminary teaching practice indicates that the model helps shorten students' debugging time and...
Yuan Tan, Qing-Yuan Zhen, XinDi Wang et al.· World Journal of Educational...· 0 citations
While AI has many productive uses, many students now use it to skip the thinking. One instinctive response from institutions and teachers is AI detection, but detection works poorly on code. This session introduces a different approach: instead of assessing just the finished code students submit, make the coding proces...
Badri Adhikari· Proceedings of International...· 0 citations
A design case study of a JupyterLab addon that delivers Socratic hints instead of direct answers, and six design hypotheses for developers of constrained AI programming assistants, addressing hint escalation, selective dialogue, context granularity, vocabulary calibration, onboarding transparency, and difficulty-aware...
Alexandre De Masi, Chen Wang, Laurent Moccozet· Proceedings of the 14th Nord...· 0 citations
Evaluating three widely used LLMs on 10 undergraduate-level digital logic questions spanning non-standard counters, JK-based state transitions, timing diagrams, frequency division, and finite-state machines suggests that they may be unreliable for core digital logic topics and can inadvertently reinforce misconceptions...
Yogeswar Reddy Thota, Setareh Rafatirad, Homayoun Houman et al.· SN Computer Science· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
