Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice

Michael J. Muller Justin D. Weisz Stephanie Houde + 2 lainnya

14 Februari 2023

Large language models (LLMs) have recently been applied in software engineering to perform tasks such as translating code between programming languages, generating code from natural language, and autocompleting code as it is being written. When used within development tools, these systems typically treat each model invocation independently from all previous invocations, and only a specific limited functionality is exposed within the user interface. This approach to user interaction misses an opportunity for users to more deeply engage with the model by having the context of their previous interactions, as well as the context of their code, inform the model’s responses. We developed a prototype system – the Programmer’s Assistant – in order to explore the utility of conversational interactions grounded in code, as well as software engineers’ receptiveness to the idea of conversing with, rather than invoking, a code-fluent LLM. Through an evaluation with 42 participants with varied levels of programming experience, we found that our system was capable of conducting extended, multi-turn discussions, and that it enabled additional knowledge and capabilities beyond code generation to emerge from the LLM. Despite skeptical initial expectations for conversational programming assistance, participants were impressed by the breadth of the assistant’s capabilities, the quality of its responses, and its potential for improving their productivity. Our work demonstrates the unique potential of conversational interactions with LLMs for co-creative processes like software development.

Cemal Yilmaz Orçun Çetin Khadija Hanifi

22 Oktober 2023

ChatGPT, an increasingly popular Large Language Model (LLM), has found widespread acceptance, especially among the younger generation, who rely on it for various tasks, such as comprehending complex course materials and tackling homework assignments. This surge in interest has drawn the attention of researchers, leading to numerous studies that delve into the advantages and disadvantages of the upcoming LLM dominant era. In our research, we explore the influence of ChatGPT and similar models on the field of software engineering, specifically from the perspective of software engineering students. Our main objective is to gain valuable insights into their usage habits and opinions through a comprehensive survey. The survey encompassed diverse questions, addressing the specific areas where ChatGPT was utilized for assistance and gathering students’ reflections on each aspect. We found that ChatGPT has garnered widespread acceptance among software engineering students, with 93% of them utilizing it for their projects. These students expressed satisfaction with the level of assistance provided, and most intend to continue using it as a valuable tool in their work. During our investigation, we also assessed the students’ awareness of the underlying technologies behind ChatGPT. Approximately half of the students demonstrated awareness of these technologies, while 38.7% had made extra efforts to explore prompt engineering to enhance ChatGPT’s productivity. However, an important finding was that 90.6% of the students reported experiencing hallucinations during their interactions with ChatGPT. These hallucinations were shared as examples, raising significant concerns that warrant further exploration and mitigation. Moreover, we delved into potential improvements and gathered valuable recommendations, which could help ChatGPT to become even more effective and dependable in its applications.

Costain Nachuma A. I. Champa Md. Fazle Rabbi + 1 lainnya

15 April 2024

The emergence of AI tools such as ChatGPT is being used to assist with software development, but little is known of how developers utilize these tools as well as the capabilities of these tools in software engineering tasks. Using the DevGPT dataset, we conduct quantitative analyses of the tasks developers seek assistance from ChatGPT and how effectively ChatGPT addresses them. We also examine the impact of initial prompt quality on conversation length. The findings reveal where ChatGPT is most and least suited to assist in the identified 12 software development tasks. The insights from this research would guide the software developers, researchers, and AI tool providers in optimizing these tools for more effective programming aid.

Guanlin Wang Sanka Rasnayaka Ganesh Neelakanta Iyer + 1 lainnya

29 Januari 2024

Large Language Models (LLMs) represent a leap in artificial intelligence, excelling in tasks using human language(s). Although the main focus of general-purpose LLMs is not code generation, they have shown promising results in the domain. However, the usefulness of LLMs in an academic software engineering project has not been fully explored yet. In this study, we explore the usefulness of LLMs for 214 students working in teams consisting of up to six members. Notably, in the academic course through which this study is conducted, students were encouraged to integrate LLMs into their development tool-chain, in contrast to most other academic courses that explicitly prohibit the use of LLMs.In this paper, we analyze the AI-generated code, prompts used for code generation, and the human intervention levels to integrate the code into the code base. We also conduct a perception study to gain insights into the perceived usefulness, influencing factors, and future outlook of LLM from a computer science student’s perspective. Our findings suggest that LLMs can play a crucial role in the early stages of software development, especially in generating foundational code structures, and helping with syntax and error debugging. These insights provide us with a framework on how to effectively utilize LLMs as a tool to enhance the productivity of software engineering students, and highlight the necessity of shifting the educational focus toward preparing students for successful human-AI collaboration.CCS CONCEPTS• Software and its engineering → Software development techniques; • Applied computing → Education.

Vandit Sharma M. Rodríguez-Triana Basile Spaenlehauer + 3 lainnya

28 Maret 2022

Over the past decade, the use of chatbots for educational purposes has gained considerable traction. A similar trend has been observed in social coding platforms, where automated agents support software developers with tasks such as performing code reviews. While incorporating code reviews and social coding platforms into software engineering education has been found to be beneficial, challenges such as steep learning curves and privacy considerations are barriers to their adoption. Furthermore, no study has addressed the role chatbots play in supporting code reviews as a pedagogical tool. To help address this gap, we developed an online learning application that simulates the code review features available on social coding platforms and allows instructors to interact with students using chatbot identities. We then embedded this application within a lesson on software engineering best practices and conducted a controlled in-class experiment. This experiment examined the effect that explaining content via chatbot identities had on three aspects: (i) students’ perceived usability of the lesson, (ii) their engagement with the code review process, and (iii) their learning gains. While our findings show that it is feasible to simulate the code review process within an online learning platform and achieve good usability, our quantitative analysis did not yield significant differences across treatment conditions for any of the aspects considered. Nevertheless, our qualitative results suggest that students expect explicit feedback when performing this type of exercise and could thus benefit from automated replies provided by an interactive chatbot. We propose to build on our current findings to further explore this line of research in future work.