Engaging with AI: An Exploratory Study on Developers' Sharing and Reactions to ChatGPT in GitHub Pull Requests

ChatGPT, as a representative Foundation Model (FM)-powered tool, has demonstrated significant potential in assisting developers with various software engineering tasks, such as code generation, program repair, and test creation. However, the timing of developers seeking assistance from ChatGPT and their perceptions of ChatGPT-generated content remain underexplored. In this paper, we analyze a dataset comprising 211 developers' shared conversations with ChatGPT within GitHub Pull Requests (PRs). Our study investigates the events in the GitHub PR timeline that precede these shared conversations, the sentiments expressed by developers when sharing these conversations, and the reactions from other developers to PR comments and descriptions that include shared conversations with ChatGPT. Our key findings are: (1) Shared conversations with ChatGPT are posted after seven distinct types of pull request timeline events, with the most frequent being comments added, PR creation, and review requests. (2) Positive sentiment is the most prevalent among developers when sharing these conversations, followed by neutral and negative sentiments. Developer reactions to comments and PR descriptions containing shared conversations are generally sparse; when they do occur, the most common reactions are (thumbs up), (heart), and (eyes). These findings provide new insights into how developers incorporate FM-powered tools into their collaborative software development workflows.