Building Developer Assistants that Think Fast and Slow
67A Google TechTalk, presented by Mayur Naik, 2022/05/19
Abstract: Prevalent developer assistants are either conventional "slow-thinking" tools based on logic reasoning, or emergent "fast-thinking" tools based on deep neural models trained on enormous amounts of code. In this talk, I will survey the strengths and limitations of these two classes of tools, and propose a new approach which combines their benefits without suffering from their drawbacks.
About the Speaker: Mayur Naik is Professor of Computer and Information Science at the University of Pennsylvania. His research lies at the intersection of programming languages and machine learning, with a current emphasis on neurosymbolic programming. He received a Ph.D. in Computer Science from Stanford University in 2008.