When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

arXiv:2306.04930v3 Announce Type: replace-cross
Abstract: AI powered code-recommendation systems, such as Copilot and CodeWhisperer, provide code suggestions inside a programmer's environment (e.g., an IDE) with the aim of improving productivity. We pursue mechanisms for leveraging signals about programmers' acceptance and rejection of code suggestions to guide recommendations. We harness data drawn from interactions with GitHub Copilot, a system used by millions of programmers, to develop interventions that can save time for programmers. We introduce a utility-theoretic framework to drive decisions …

abstract aim arxiv code code suggestions codewhisperer copilot cs.hc cs.lg cs.se environment feedback guide harness human human feedback ide improving inside productivity programmer programmers programming recommendation recommendations recommendation systems show suggestions systems type