The reviewed record of science sign in
Pith

arxiv: 2206.15000 · v3 · pith:FMEI6E6B · submitted 2022-06-30 · cs.HC · cs.PL

Grounded Copilot: How Programmers Interact with Code-Generating Models

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:FMEI6E6Brecord.jsonopen to challenge →

classification cs.HC cs.PL
keywords copilotprogrammingassistantscode-generatingfacegroundedinteractmode
0
0 comments X
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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs

    cs.AI 2026-06 unverdicted novelty 5.0

    An LLM-driven evolutionary framework generates executable trading strategies as Python code and uses a meta-loop to evolve the prompts that guide synthesis.

  2. Reliability of AI Bots Footprints in GitHub Actions CI/CD Workflows

    cs.SE 2026-04 unverdicted novelty 5.0

    Large-scale analysis of AI bot PRs shows Copilot and Codex achieve the highest CI/CD success rates but more frequent AI contributions correlate with reduced workflow reliability.

  3. Teaching Astronomy with Large Language Models

    physics.ed-ph 2025-06 unverdicted novelty 5.0

    Structured integration of LLMs in astronomy education, including a domain-specific tutor and documentation requirements, leads to improved AI literacy and reduced student reliance on AI over the semester.