ICSE 2024
Fri 12 - Sun 21 April 2024 Lisbon, Portugal

AI-based tools for software development are widely discussed in academic literature. They promise to boost software development performance, especially in code creation. This paper collects insights from practitioners about the use and implications of AI assistance in industrial software development, with a focus on SMEs. Through interviews with five developers from three software development organization, we gathered and analyzed the experiences made in industrial practice, and we identified lessons learned and open challenges. ChatGPT and Copilot are used in industry projects. While they are considered useful for many code-related development activities, their integration in the development workflow remains mostly shallow. Contradicting observations about speed-ups due to AI support in development are reported. Legal issues are a minor concern although awareness exists.

Sat 20 Apr

Displayed time zone: Lisbon change

09:00 - 10:30
Session 1: Welcome & Opening + Keynote 1 + Full PapersLLM4Code at Luis de Freitas Branco
Chair(s): Lin Tan Purdue University
09:00
10m
Day opening
Welcome & Opening
LLM4Code
Prem Devanbu University of California at Davis, Yiling Lou Fudan University, Lin Tan Purdue University, Lingming Zhang University of Illinois at Urbana-Champaign
09:10
50m
Keynote
Code Llama: Open Foundation Models for Code
LLM4Code
10:00
10m
Talk
Industrial Experience Report on AI-Assisted Coding in Professional Software Development
LLM4Code
Rudolf Ramler Software Competence Center Hagenberg (SCCH), Lukas Fischer Software Competence Center Hagenberg GmbH, Michael Moser Software Competence Center Hagenberg GmbH, Markus Nissl Building Digital Solutions 421 GmbH, Rene Heinzl Building Digital Solutions 421 GmbH
10:10
10m
Talk
Gauging Tech Community Acceptance of Rapid Prototyping in Unfamiliar Programming Languages using LLM Chatbots
LLM4Code
Krerkkiat Chusap Ohio University, Chang Liu
10:20
10m
Talk
LLM4TDD: Best Practices for Test Driven Development Using Large Language Models
LLM4Code
Sanyogita Piya The University of Texas at Arlington, Allison Sullivan University of Texas at Arlington