In this episode, we have Alessio Buscemi, a software engineer at Lifeware SA. Alessio was a post-doctoral researcher at the University of Luxembourg. He joins us to discuss his paper, A Comparative Study of Code Generation using ChatGPT 3.5 across 10 Programming Languages.
Alessio shared his thoughts on whether ChatGPT is a threat to software engineers. He discussed how LLMs can help software engineers become more efficient.
Delving into his study, he discussed how he set up his experiment and the kind of tasks he fed into ChatGPT. He discussed his results, particularly the programming languages ChatGPT performed the best on, as well as the domains it does better on. He also shared factors that affect the performance of ChatGPT in coding tasks.
Alessio shared some of his future research ideas. To learn more about Alessio’s work, follow him on Linkedin.
I earned my Ph.D. in Computer Engineering from the University of Luxembourg in March 2022. Following the completion of my Ph.D., I continued my research as a Postdoctoral researcher for an additional year. During this time, my research primarily focused on in-vehicle networking, mostly Controller Area Network reverse engineering.