Productivity Assessment of Neural Code Completion
This addresses the problem of measuring productivity for neural code completion tools in software development, though it is incremental as it focuses on perception rather than objective productivity gains.
The study investigated how developers perceive productivity when using GitHub Copilot, finding that acceptance rates of suggestions, rather than long-term code persistence, drive their perception.
Neural code synthesis has reached a point where snippet generation is accurate enough to be considered for integration into human software development workflows. Commercial products aim to increase programmers' productivity, without being able to measure it directly. In this case study, we asked users of GitHub Copilot about its impact on their productivity, and sought to find a reflection of their perception in directly measurable user data. We find that the rate with which shown suggestions are accepted, rather than more specific metrics regarding the persistence of completions in the code over time, drives developers' perception of productivity.