研究：AI 编码智能体生成更多代码，但并未带来更多软件产出
Harvard 研究人员 Fiona Chen 与 James Stratton 基于 Jellyfish 汇总的分析数据发现，AI 编码工具提升的编码阶段效率被下游环节吸收，人工代码评审成为整体效率的显著瓶颈。
Ars Technica：AI· Kyle Orland·2026-10-10 03:43· 22 分钟前AI 评分62
AI coding agents generate more code, but not more software
AI 导读
Harvard 研究人员 Fiona Chen 与 James Stratton 基于 Jellyfish 汇总的分析数据（覆盖 700 余家软件开发企业、超 70 万名员工、2021 年至 2026 年 3 月的 3 亿个工作事件）发现，人工代码评审成为 AI 编码工具整体效率的显著瓶颈。
正文
Anyone who's even tangentially associated with computer programming knows that modern AI coding assistants and agents can be incredibly efficient at generating huge amounts of functional code. But coders making use of those tools also know better than to trust the accuracy of that code, meaning substantial effort needs to be spent reviewing any AI-generated output.
A recent study of actual coding practices across hundreds of firms finds that human code review forms a significant "bottleneck" for the overall efficiency of AI coding tools, resulting in "little evidence that firms increase software output or reduce employment" by using them. Any efficiency increased during the actual coding phase, the study authors find, is "absorbed by downstream constraints in the production process"; as "the code review process significantly increases in length, pull requests are more likely to require revisions, and reviewers leave more comments."
Cut once, measure twice
To come to these conclusions, Harvard University researchers Fiona Chen and James Stratton made use of aggregated analytics data from Jellyfish, which measures the granular output of engineering teams. That data encompasses 300 million individual "work events" (e.g. commits and pull requests) and issue management software data across more than 700,000 employees at over 700 relevant software development firms from 2021 through March of 2026.
来源：Ars Technica：AI · arstechnica.com
来源：RadarAI · aihot.news