ML-Enhanced Code Completion Improves Developer Productivity (2022)

Update — 2022/09/06: This post has been updated to remove a statement about an observed reduction in context switches that could not be confirmed with statistical significance. The increasing complexity of code poses a key challenge to productivity in software engineering. Code completion has been an essential tool that has helped mitigate this complexity in integrated development environments (IDEs). Conventionally, code completion suggestions are implemented with rule-based semantic engines (SEs), which typically have access to the full repository and understand its semantic structure. Recent research has demonstrated that large language models (e.g., Codex and PaLM) enable longer and more complex code suggestions, and as a result, useful products have emerged (e.g., Copilot). However, the question of how code completion powered by machine learning (ML) impacts developer productivity, beyond perceived productivity and accepted suggestions, remains open. Today we describe how we com ... Read full article.