一人用AI+双重保障，120小时完成五平台绘图软件开发
Jas: AI-Paired Engineering as a Revival of N-Version Programming
- 用可执行的YAML规范做唯一真相源，多版本并行实现自动校验
- 5个平台共用2.3万行规格说明，代码量0到9.5万行不等
- 适合想用AI快速验证多端原型的开发者或小团队
本文报告了一项人工智能辅助的软件工程案例研究：一名开发者在约120个晚间工时内，使用Rust、Swift、OCaml、Python和浏览器平台，实现了五个可用的矢量绘图应用版本。该方法结合了AI辅助实现与两项保障机制——以精确可执行的YAML规范作为单一真实来源，以及多个并行实现构成内置差分测试层。五个版本共享一份23,000行的规范文件；各平台原生代码量从0到约95,000行不等，反映了规范的灵活性。作者认为，在上述双重保障下，人工智能辅助工程使原本需多名开发者数年完成的工作成为可能，并将此方法视为1980年代因成本过高被放弃的N版本编程思想的复兴。论文披露了具体成果及单人案例的真实局限。
原文摘要 · Abstract (English)
I report a case study in AI-paired software engineering: five working ports of a vector illustration application across Rust, Swift, OCaml, Python, and browser-based platforms, built by a single developer in approximately 120 evening hours. The methodology pairs AI-assisted implementation with two safeguards -- a precise executable YAML specification serving as the single source of truth, and parallel implementations functioning as a built-in differential-testing layer. The five ports share a 23{,}000-line specification; per-port native code ranges from 0 to roughly 95{,}000 lines, reflecting the specification's escape hatch. I argue that AI-paired engineering, conditional on these two safeguards, makes feasible scope of work that conventionally requires multiple developer-years, and frame the methodology as a revival of N-version programming, a 1980s approach abandoned on cost grounds that AI changes. The paper reports concrete artifacts and honest limitations of the single-developer case study.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。