Answers are grounded in this paper and cite their sources.
This article discusses the possibilities and limitations of using large language models (LLMs) in software development with applications in computational electromagnetics. Three tasks are discussed: code translation, code generation, and code description. The tests showed that LLMs are generally very useful. Even when errors occurred, they can provide useful hints to find a solution.
No takes yet. Share an insight, caveat, or question.
Leandro Carísio Fernandes (2023) studied this question.