Has the day we all have been waiting for really arrived? Have advances in deep learning and machine learning (ML) finally reached a turning point and have started to produce “accurate enough” assistants to help us in a variety of tasks, including software development? Are large language models (LLM) going to turn us all into better writers, artists, translators, programmers, health care workers, not to mention software engineers? Or are we at a risky turning point where we will not only be able to not separate AI-generated content from user created ones, but will be drawn in perfect sounding yet fake and incorrect information, not to mention faulty programs?

Taking advantage of AI in supporting software engineering tasks has been a journey researchers and tool vendors have been on for a long time. What is new, however, is the ubiquitously available computing resources, off-the shelf ML solutions, and APIs which allow others to take advantage of well-working models. The increasing availability of software engineering data and ML solutions on one hand presents a turning point opportunity for re-envisioning how AI-based tools can support developers. On the other hand, we need to be reminded early and often that no automation can fully replace discipline, rigor, and human judgement power. We need to be bold in experimenting with the potential that AI-augmented software development may provide in improving lives of developers and quality of systems, yet we also need to be cautious and not forget fundamentals of engineering ethics and rigor. In this talk, I will walk through the recent advances in LLMs and AI-based tools and bots and how they in fact may change how we conduct software development tasks if we position them appropriately in our software development lifecycles.

Dra. Ipek Ozkaya, Carnegie Mellon University Software Engineering Institute (SEI)

Ipek Ozkaya is the technical director of Engineering Intelligent Software Systems group at Carnegie Mellon University Software Engineering Institute (SEI). Her main areas of expertise and interest include software architecture, software design automation, and managing technical debt in software-reliant and AI-enabled systems. At the SEI she has worked with several government and industry organizations in domains including avionics, power and automation, IoT, healthcare, and IT. Ozkaya is the co-author of a practitioner book titled Managing Technical Debt and is the Editor-in-Chief of IEEE Software Magazine. She holds a PhD in Computational Design from Carnegie Mellon University.