Resource Automation + AI Generative AI

Better Together? An Evaluation of AI-Supported Code Translation

This research explores how software engineers are able to work with generative machine learning models. The results explore the benefits of generative code models and the challenges software engineers face when working with their outputs. The authors also argue for the need for intelligent user interfaces that help software engineers effectively work with generative code…

A controlled study found that software engineers produced higher-quality code with fewer errors when using AI-generated translations for Java-to-Python code conversion, even though the AI outputs were not perfect.

The use of AI shifted the task from code production to code review, saving time and providing learning opportunities, but users still needed to identify and fix errors. The research highlights the potential of generative code models to enhance human performance and the importance of intelligent user interfaces for effective use.