REVIEW 4 cited by
Grounded Copilot: How Programmers Interact with Code-Generating Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Powered by recent advances in code-generating models, AI assistants like Github Copilot promise to change the face of programming forever. But what is this new face of programming? We present the first grounded theory analysis of how programmers interact with Copilot, based on observing 20 participants--with a range of prior experience using the assistant--as they solve diverse programming tasks across four languages. Our main finding is that interactions with programming assistants are bimodal: in acceleration mode, the programmer knows what to do next and uses Copilot to get there faster; in exploration mode, the programmer is unsure how to proceed and uses Copilot to explore their options. Based on our theory, we provide recommendations for improving the usability of future AI programming assistants.
Forward citations
Cited by 4 Pith papers
-
Code Shaping: Iterative Code Editing with Free-form AI-Interpreted Sketching
Free-form sketch annotations on and around code can be interpreted by a large language model to produce iterative code edits, and a three-stage study with 18 programmers yields design guidelines for this interaction paradigm.
-
Exploring the Challenges and Opportunities of AI-assisted Codebase Generation
Developers prompting codebase-level AI assistants are often dissatisfied with generated code, citing missing functionality, poor code quality, and communication gaps, despite varied prompting strategies.
-
Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights
SBC is a hybrid metric that reverse-generates requirements from LLM-written code and scores their semantic, lexical, and completeness match to the original requirement, but its validity is not established.
-
Adoption of Generative Artificial Intelligence in the German Software Engineering Industry: An Empirical Study
In a survey of 109 German developers plus 18 interviews, GenAI productivity gains cluster among 'power users'; junior and senior developers perceive prompting differently, and limited codebase context is a major barrier.
Discussion (0). Continue with ORCID to comment.