Anthropic 重构源代码管理系统

Anthropic 重构源代码管理系统（来源）Anthropic 这篇文章很有意思，介绍了他们为何以及如何构建一套替代 Git 的定制系统。其背景是过去六个月中，代码变更速率急剧上升。

2026 年 5 月，Anthropic 平均每天合并约 2,500 项代码变更；截至 9 月，我们每天合并的变更已超过 30,000 项。

他们提供了一张展示这些变更的数据图表。我让 Claude 修改了他们的图表（代码在这里），为 2026 年各模型的公开发布日期添加了标记：

这里展示的是公开发布日期，而非模型向 Anthropic 内部开放使用的日期。我猜测，Fable/Mythos 类模型的引入，是代码开发速度提升的关键因素之一。

“Antique”是他们的新代码审查系统。源代码管理系统名为 Scion；在我看来，它像是重新发明了一种类似 Subversion 的集中式源代码管理系统。他们面临的需求相当极端：

仅主分支的历史记录就接近 100 GB，而一个 压缩后的 工作副本也超过 25 GB。仅 CI 每天就会执行大约 2,500 万次代码检出，尚未计入开发者环境、Agent 沙箱和研究任务。若以简单直接的方式获取这些内容，每天的 Git 流量将超过 600 PB。

这套新系统由一个 7 人团队构建，并在 5 个月内完成了从 Git 的迁移。

顺带一提，我最近也在自己的项目中尝试对抗式审查：让一个模型主动寻找缺陷（我经常让 Claude 和 GPT 相互较量）。文章中的这段说明与我的亲身体验一致：

Anthropic 也广泛采用对抗式审查。尽管这种方法在许多方面极其有效，但它也可能陷入短视，因此需要经验丰富的工程师引导 Claude，避免它为了应对假设性的担忧而对系统局部进行过度设计。

Redesigning source control at Anthropic (via) 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.

In May 2026, Anthropic averaged around 2,500 code changes merged per day; as of September, we merged over 30,000 per day.

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:

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.

"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:

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.

The new system was built by a team of seven people, and the migration from Git was completed in five months.

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:

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.