arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.07830cs.SE
收藏

与Copilot一起:22位AI系统开发者想要构建的系统

To Copilot and Beyond: 22 AI Systems Developers Want Built

Oregon State University(俄勒冈州立大学);Microsoft Research(微软研究院)

Rudrajit Choudhuri, Christian Bird, Carmen Badea, Anita Sarma

AI总结:

本文通过调研860名微软开发者,识别出22个AI系统需求,涵盖五个任务类别。研究发现开发者希望AI在早期工作流中嵌入质量信号,同时限制其权限和隐私,揭示了AI辅助开发中的'有界委托'模式。

摘要:

开发者花费约十分之一的工作日编写代码,但大多数AI工具针对的是这一比例。本文探讨应构建什么以满足剩余需求。我们调研了860名微软开发者,了解他们希望AI提供支持的领域以及不希望AI介入的领域。通过人机协作、多模型委员会基于主题的分析,我们识别出22个AI系统,涵盖五个任务类别。对于每个系统,我们描述其解决的问题、构建的难点以及开发者对行为的限制。研究发现AI辅助开发中存在向右转移的负担:开发者希望系统在工作流早期嵌入质量信号以跟上加速的代码生成,同时在整个过程中实施显式权限范围、可追溯性、不确定性信号和最小特权访问。这种紧张揭示了我们称为'有界委托'的模式:开发者希望AI吸收围绕其工作的装配工作,但从未涉及其自身。该边界追踪他们专业身份的位置,表明AI工具的价值可能更多在于其停止的位置和精确程度,而不仅仅是其执行的内容。

英文摘要:

Developers spend roughly one-tenth of their workday writing code, yet most AI tooling targets that fraction. This paper asks what should be built for the rest. We surveyed 860 Microsoft developers to understand where they want AI support, and where they want it to stay out. Using a human-in-the-loop, multi-model council-based thematic analysis, we identify 22 AI systems that developers want built across five task categories. For each, we describe the problem it solves, what makes it hard to build, and the constraints developers place on its behavior. Our findings point to a growing right-shift burden in AI-assisted development: developers wanted systems that embed quality signals earlier in their workflow to keep pace with accelerating code generation, while enforcing explicit authority scoping, provenance, uncertainty signaling, and least-privilege access throughout. This tension reveals a pattern we call "bounded delegation": developers wanted AI to absorb the assembly work surrounding their craft, never the craft itself. That boundary tracks where they locate professional identity, suggesting that the value of AI tooling may lie as much in where and how precisely it stops as in what it does.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑