Anthropic 自研 Scion 替代 Git 的工程复盘
Redesigning source control at Anthropic
AI 公司应对高并发代码协作的工程实践，Scion 的集中式设计与对抗性审查取舍对 Agent 时代研发有参考价值。
Redesigning source control at Anthropic
Anthropic 对源代码控制的重构
Interesting piece from Anthropic describing why and how they built their own custom alternative to Git, based on the dramatic increase in rate of changes to their code after the past six months.
Anthropic 发布了一篇有趣的文章，描述了他们在过去六个月中代码变更频率急剧增加后，为何以及如何构建了自己的 Git 定制替代方案。
In May 2026, Anthropic averaged around 2,500 code changes merged per day; as of September, we merged over 30,000 per day.
在 2026 年 5 月，Anthropic 平均每天合并约 2,500 次代码变更；截至 9 月，我们每天合并超过 30,000 次。
They included a chart showing those changes. I had Claude modify their chart (code here) to add markers for the public releases of each of their models in 2026:
他们包含了一张展示这些变更的图表。我让 Claude 修改了他们的图表（代码见此处），为 2026 年每个模型的公开发布添加了标记：
This shows public release dates, not the date when models became available for Anthropic's internal use. My guess is that the introduction of Fable/Mythos class models is a key factor in the increased coding velocity.
这显示的是公开发布日期，而非模型可供 Anthropic 内部使用的日期。我的猜测是，Fable/Mythos 系列模型的引入是导致编码速度提升的关键因素。
"Antique" is their new code review system. The source control system is called Scion, and sounds to me like a reinvention of centralized source control along the lines of Subversion. They had some pretty extreme requirements:
"Antique" 是他们新的代码审查系统。源代码控制系统名为 Scion，在我看来，它类似于 Subversion 风格的集中式源代码控制的重新发明。他们有一些相当极端的需求：
The history of our main branch alone is almost 100 GB, and a compressed working copy is over 25 GB. We perform on the order of 25 million code checkouts per day for CI, before counting developer environments, agent sandboxes, and research jobs. Fetched naively, that would be over 600 PB of git traffic per day.
仅主分支的历史记录就接近 100 GB，压缩后的工作副本超过 25 GB。我们在计算开发者环境、代理沙箱和研究任务之前，每天执行约 2,500 万次代码检出以用于 CI。如果简单获取，每天的 git 流量将超过 600 PB。
The new system was built by a team of seven people, and the migration from Git was completed in five months.
新系统由一个七人团队构建，从 Git 迁移到该系统耗时五个月完成。
As an aside, I've been trying adversarial review in my own projects recently, where you have a model try and find flaws (I often play Claude and GPT off against each other). This note from the article reflected my own experience with that:
顺便提一下，我最近在自己的项目中尝试对抗性审查，即让模型试图找出缺陷（我经常让 Claude 和 GPT 相互竞争）。文章中的这一备注反映了我对此的实际体验：
Anthropic also makes extensive use of adversarial review, and, while this is incredibly effective in many ways, it can also be myopic, so skilled engineers needed to steer Claude away from over-engineering parts of the system in response to hypothetical concerns.
Anthropic 也广泛使用对抗性审查，虽然这在许多方面非常有效，但也可能具有短视性，因此需要熟练的工程师引导 Claude 避免针对假设性问题过度设计系统的某些部分。
Via Hacker News
来源：Hacker News
Tags: git, migrations, version-control, ai, generative-ai, llms, anthropic, agentic-engineering
标签：git, migrations, version-control, ai, generative-ai, llms, anthropic, agentic-engineering
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力