Generative AI has become a disruptive force in software development, with applications spanning a wide range of tasks. However, our recent empirical studies across various tasks reveal a consistent pattern: large language models automate substantial portions of the work, yet often produce results that are almost right. The remaining incorrect or incomplete work is then left to human developers, who must validate, repair, and reason about AI-generated changes.

In this talk, I explore two intertwined questions that arise from this reality. First, what is the cost of AI’s incomplete work, especially the cognitive overhead involved for the developer? Second, and more critically, what happens when increasing reliance on AI affects the very skills developers need to finish incomplete tasks, a concern that becomes particularly visible in educational settings?

I am an Associate Professor of Computer Science at New York University Abu Dhabi, and an adjunct professor at the University of Alberta. My research provides automated support tools that help software developers accomplish their tasks more efficiently. My recent work focusing on supporting developers as they use software libraries, including the initial selection process, correctly using the library’s API, and potential migration to newer alternative libraries.