Large Language Models (LLMs) have the potential to fundamentally change the way people engage in computer programming. Agent-based modeling (ABM) has become ubiquitous in natural and social sciences and education, yet...
详细信息
ISBN:
(纸本)9798400703300
Large Language Models (LLMs) have the potential to fundamentally change the way people engage in computer programming. Agent-based modeling (ABM) has become ubiquitous in natural and social sciences and education, yet no prior studies have explored the potential of LLMs to assist it. We designed NetLogo Chat to support the learning and practice of NetLogo, a programming language for ABM. To understand how users perceive, use, and need LLM-based interfaces, we interviewed 30 participants from global academia, industry, and graduate schools. Experts reported more perceived benefits than novices and were more inclined to adopt LLMs in their workflow. We found significant differences between experts and novices in their perceptions, behaviors, and needs for human-AI collaboration. We surfaced a knowledge gap between experts and novices as a possible reason for the benefit gap. We identified guidance, personalization, and integration as major needs for LLM-based interfaces to support the programming of ABM.
Generative artificial intelligence (GAI) has the potential to transform software development practices with prior research indicating significant overall enhancements in developers' productivity. However, there ex...
详细信息
ISBN:
(纸本)9783031611742;9783031611759
Generative artificial intelligence (GAI) has the potential to transform software development practices with prior research indicating significant overall enhancements in developers' productivity. However, there exists a lack of design knowledge for organization-specific GAI systems to assist software development. To bridge this research gap, we derive a design framework for collaborative GAI systems in software development following design science research. Specifically, we conducted eight interviews with practitioners and reviewed extant literature to formulate design requirements and design principles. In our analysis of the literature and our qualitative data, we identify problems surrounding usability, data privacy, hallucination and transparency. To address these problems, we propose GAI system designs that enable user-centricity, data protection, quality control and communication. Our findings contribute valuable design knowledge to the field of generative AI and organizational software development practices.
暂无评论