There is a growing trend of using general-purpose large language models (LLMs), such as ChatGPT, in software development workflows, often outside traditional IDEs or engineering practices. One emerging phenomenon is vibe coding, which refers to a fluid, intuitive, and emotionally attuned development style shaped by conversational AI tools, music, mood, and ambient factors. I propose research that investigates why software practitioners are drawn to general-purpose LLMs and how these tools fit into and enhance vibe coding experiences. In particular, I aim to understand how these environments affect productivity and well-being, especially for software practitioners with mental health conditions (e.g., ADHD, anxiety, depression). By examining both the technical and psychological aspects of general-purpose LLM use, including but not limited to vibe coding, I intend to facilitate the development of improved tools, settings, and practices that promote a more balanced and adaptable approach to LLM-driven software development.

The rapid integration of AI-assisted tools such as ChatGPT, GitHub Copilot, and Gemini into software development has reshaped how practitioners perform tasks, collaborate, and manage their workloads. While these tools offer productivity gains, they also introduce new job demands, such as cognitive overload, emotional stress, and blurred work-life boundaries that can affect practitioners’ well-being. We designed a research study to investigate the short and long-term well-being impacts of AIassisted tools on software practitioners, using the Job DemandsResources (JD-R) model as a guiding framework. Through a mixed-methods study combining survey and interview data, we aim to identify both beneficial and harmful patterns emerging from use of AI-assisted tools. Our findings thus far suggest both positive and negative impacts of AI-Assisted tools on software practitioner well-being. We also found significant differences in impact between practitioners with and without neurocognitive conditions, underscoring the need for inclusive tool design and thoughtful organizational policies. This research contributes theoretical insights into the evolving human-tool relationship in software development and aims to inform the ethical and sustainable integration of AI into developer workflows.

Automated program repair, also known as APR, is an approach for automatically repairing software faults. There is a large amount of research on automated program repair, but very little offers in-depth insights into how practitioners think about and employ APR in practice. To learn more about practitioners' perspectives and experiences with current APR tools and techniques, we administered a survey, which received valid responses from 331 software practitioners. We analyzed survey responses to gain insights regarding factors that correlate with APR awareness, experience, and use. We established a strong correlation between APR awareness and tool use and attributes including job position, company size, total coding experience, and preferred language of software practitioners. We also found that practitioners are using other forms of support, such as co-workers and ChatGPT, more frequently than APR tools when fixing software defects. We learned about the drawbacks that practitioners encounter while utilizing existing APR tools and the impact that each drawback has on their practice. Our findings provide implications for research and practice centered on development, adoption, and use of APR.

Survey research, while common, has known challenges and limitations. In this paper, we discuss the challenges and concerns of conducting research using online survey in the age of widespread development and use of generative AI technologies. We base our discussion on our recent experiences conducting survey research to better understand software practitioners’ knowledge of and experience with automated program repair (APR). In our efforts, we encountered both anticipated and unexpected challenges, much of which stemmed from advancements in AI-assisted automation (e.g., generative AI). For example, we found that many of the open ended responses provided were likely generated by AI. Based on our experiences, we outline how we mitigated or handled these challenges and discuss opportunities for improving survey design and administration to ensure high quality research and outcomes in the age of advanced and widely available AI technologies.

There is an increasing utilization of non-development large language models (LLMs), such as ChatGPT, in software development despite the availability of dedicated software development tools. I propose research that investigates the reasons behind use of non-development LLM tools and the impact they have on productivity and well-being of software practitioners, particularly those with diagnosed mental health disorders. I will use insights from these efforts to analyze the advantages and disadvantages of non-development LLMs in order to generate recommendations and interventions that will facilitate the effective integration and use of non-development LLM tools in software development.