Generative AI in Software Engineering

The field of software engineering is undergoing a significant transformation with the integration of generative AI. Recent developments have shown that generative AI can be used to boost productivity in tasks such as unit test engineering, and can also enable new development styles such as chat-oriented programming and 'vibe coding'. However, these AI-assisted workflows also raise concerns about control, output quality, and learning, particularly for novice developers. The use of generative AI in software project management is also becoming increasingly popular, with practitioners perceiving it as an 'assistant' or 'copilot' rather than a replacement for human project managers.

Noteworthy papers in this area include: Generative AI and the Transformation of Software Development Practices, which examines how AI-assisted techniques are changing software engineering practice. What Slows Down FMware Development, which investigates the challenges developers encounter when building applications and infrastructures around foundation models. A Survey of Vibe Coding with Large Language Models, which provides a comprehensive review of the vibe coding ecosystem and establishes theoretical foundations and practical frameworks for this transformative development approach.

Sources

How Students Use Generative AI for Software Testing: An Observational Study

Generative AI and the Transformation of Software Development Practices

Generative AI for Software Project Management: Insights from a Review of Software Practitioner Literature

Interoperability From OpenTelemetry to Kieker: Demonstrated as Export from the Astronomy Shop

What Slows Down FMware Development? An Empirical Study of Developer Challenges and Resolution Times

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs

Cracking CodeWhisperer: Analyzing Developers' Interactions and Patterns During Programming Tasks

Show Your Title! A Scoping Review on Verbalization in Software Engineering with LLM-Assisted Screening

(R)evolution of Programming: Vibe Coding as a Post-Coding Paradigm

A Survey of Vibe Coding with Large Language Models

The EmpathiSEr: Development and Validation of Software Engineering Oriented Empathy Scales

Software Testing Education and Industry Needs - Report from the ENACTEST EU Project

Built with on top of