On the Design of AI-powered Code Assistants for Notebooks

McNutt, Andrew; Wang, Chenglong; DeLine, Robert; Drucker, Steven M.

doi:10.1145/3544548.3580940

Cited by 32 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once they determined their desired image style, the process of refining images transitioned back to the exploitation mode. Such observation of the different modes' user behavior is similar to the previous studies on how programmers interact with AI programming assistants in acceleration mode and exploration mode [4,44]. Our study results further imply that PromptCharm can support both modes effectively.…”

Section: Exploration Vs Exploitationsupporting

confidence: 88%

PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement

Wang,

Huang,

Song

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

Section: Exploration Vs Exploitationsupporting

confidence: 88%

PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement

Wang,

Huang,

Song

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…We posit that it is reasonable, too, to expect the widespread adoption of generative technologies in visualization creation within the coming decade. Similar studies as our own have been carried out in other domains, including newsrooms graphics [LQC22], visual marketing [MV22], computational notebooks [MWDD23] and construction scheduling [PMdS23]. Our study differs from these its focus on the particular visualization practice and design.…”

Section: Background and Related Workmentioning

confidence: 86%

Doom or Deliciousness: Challenges and Opportunities for Visualization in the Age of Generative Models

Schetinger

Bartolomeo

El‐Assady³

et al. 2023

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another study explored the integration between computational notebooks with LLMs and emphasized the role of the domain (in this case, data science) on LLM-based interface design [55].…”

Section: Llm-based Interfaces For Learning Programming and Modelingmentioning

confidence: 99%

Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chat

Chen,

Lu,

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Large Language Models (LLMs) have the potential to fundamentally change the way people engage in computer programming. Agentbased 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 LLMbased interfaces to support the programming of ABM.

show abstract

On the Design of AI-powered Code Assistants for Notebooks

Cited by 32 publications

References 47 publications

PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement

PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement

Doom or Deliciousness: Challenges and Opportunities for Visualization in the Age of Generative Models

Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chat

Contact Info

Product

Resources

About