Why Large Language Models will (not) Kill Software Engineering Research

Over the last decade, we have witnessed a flourishing activity in the application of deep learning techniques to solve software engineering problems that were poorly addressed in the past, or not addressed at all. In this context, researchers put effort into creating specialized representations and models, hence giving a tangible, conceptual contribution beyond the simple application. With the advent of Large Language Models, such contributions were surpassed, and this was possible because big techs had the availability of data and infrastructure. As such models are pretty good at solving many software engineering problems, where would research in software engineering, and, specifically, in recommender systems go? Will artificial intelligence research kill it? Fortunately, we should not forget that software engineering is about people, and this is where I believe there will be a lot of room for novel research. Software engineering researchers have the knowledge to understand how LLMs fit (or do not fit) in a development context, by properly pondering, for example, human, ethical, and legal factors. Also, software engineering researchers have a strong empirical background to evaluate the effectiveness of such models where state-of-the-art measurements might not suffice.