本文为原文前 6,000 字符的节选翻译，完整内容请查看原文。

AI coding agents generate more code, but not more software

Anyone who has 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.

任何与计算机编程有哪怕一点点接触的人都知道，现代人工智能编程助手和代理在生成大量功能性代码方面效率极高。但使用这些工具的程序员也深知不能盲目信任代码的准确性，这意味着必须投入大量精力来审查人工智能生成的任何输出。

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.”

最近一项针对数百家公司实际编程实践的研究发现，人工代码审查构成了人工智能编程工具整体效率的重大“瓶颈”，导致“几乎没有证据表明公司通过使用这些工具增加了软件产出或减少了就业”。研究作者发现，在实际编码阶段提高的任何效率都被“生产过程中的下游约束所抵消”；因为“代码审查过程的耗时显著增加，拉取请求（pull requests）更有可能需要修改，且审查人员留下的评论也更多了。”

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.

为了得出这些结论，哈佛大学的研究人员 Fiona Chen 和 James Stratton 利用了来自 Jellyfish 的汇总分析数据，该平台用于衡量工程团队的细粒度产出。这些数据涵盖了从 2021 年到 2026 年 3 月期间，超过 700 家相关软件开发公司的 70 多万名员工所产生的 3 亿个独立“工作事件”（如提交和拉取请求）以及问题管理软件数据。

In terms of raw code being produced, the results are clear and stark. The introduction of AI coding agents at a firm leads to a 30 percent increase in total lines of code generated, a 20 percent rise in the number of total commits, and a 23 percent increase in pull requests on average, the researchers write. But all that extra code doesn’t translate directly into improved software output on the firm level.

就产生的原始代码而言，结果清晰而鲜明。研究人员写道，公司引入人工智能编程代理后，生成的代码总行数增加了 30%，提交总数增加了 20%，拉取请求平均增加了 23%。但所有这些额外的代码并不能直接转化为公司层面的软件产出提升。

The reason for that discrepancy can be found directly in the code review process, which takes markedly longer on average after the introduction of AI coding agents. Overall, the average “review process” time between a pull request getting submitted and it being merged into the codebase balloons 49 percent on average after AI agents are introduced.

这种差异的原因可以直接在代码审查过程中找到，在引入人工智能编程代理后，该过程平均耗时明显变长。总体而言，在引入人工智能代理后，从提交拉取请求到将其合并到代码库之间的平均“审查过程”时间平均激增了 49%。

While AI could also theoretically help with this review process, the researchers found that, so far, that impact has been marginal. Although 80 percent of measured firms used some form of AI code review by March 2026, AI agents were only responsible for 23.3 percent of all review comments and 10.8 percent of all pull requests, suggesting humans were still responsible for the vast majority of this work.

虽然从理论上讲，人工智能也可以帮助进行这种审查过程，但研究人员发现，到目前为止，这种影响微乎其微。尽管到 2026 年 3 月，80% 的受测公司使用了某种形式的人工智能代码审查，但人工智能代理仅负责了所有审查评论的 23.3% 和所有拉取请求的 10.8%，这表明人类仍然负责这项工作中的绝大部分。

For now, though, letting AI write your code looks like a double-edged sword, with increases in coding speed counteracted by similar increases in human code review time and effort. It’s the kind of result that makes us wonder if the considerable time and expense to get AI coding agents working is really worth it for most companies.

然而就目前而言，让人工智能编写代码看起来是一把双刃剑，编码速度的提升被人工代码审查时间和精力的相应增加所抵消。这种结果不禁让我们怀疑，对于大多数公司来说，投入大量时间和金钱来让人工智能编程代理发挥作用是否真的值得。