Anthropic 自研版本控制系统放弃离线，dex 分析这一取舍背后的思路转变
anthropic built their own git. Most interesting mental shift here, and if you buy that changing code happens more and more autonomously, faster*, then this will
dex 指出 Anthropic 自研的版本控制系统不再支持离线，客户端必须连接中心服务器才能工作，而 Git 的设计是任何客户端都能离线服务仓库。他认为如果未来代码变更每天发生 1000 次且没有人类介入，版本控制系统实际上就成了生产环境的一部分，因此可以像生产系统一样由 SRE 团队维护在线，并借此把部分处理卸载到服务端、重新设计存储方式。他同时表示自己并不完全认同这一前提，但实验室确实在推动让智能体根据故障、功能请求、用户行为变化等信号直接改动已部署代码。Anthropic 工程博客称其 5 月每天合并约 2500 次代码变更，9 月超过 30000 次，并在五个月内把 monorepo 从 git 完整迁移到新系统。
推荐理由
AI 评分 52
从 Anthropic 自研 VCS 的离线取舍切入，讨论代码自主变更后版本控制与生产环境的关系变化。
主题
查看原帖New on our Engineering blog: Creating in-house source control. In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale. Here, we share how we built a new version control system—and fully migrated our…
展开完整原文
New on our Engineering blog: Creating in-house source control. In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale. Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: https://t.co/wzNkwHs7IN
正文
当前显示原文，中文全文译文尚未就绪。
anthropic built their own git. Most interesting mental shift here, and if you buy that changing code happens more and more autonomously, faster*, then this will make a ton of sense:
Git was designed so that any client could serve the repo. Fully offline, your *build time* dev stack is never in the hot path for your *run time* deployment.
Anthropics new version control system (VCS) does not work offline. There’s a central server which must be reachable for clients to function. They found a bunch of benefits to doing it this way.
At first this sounds wild. Today if GitHub is down, you can’t pull or push or merge. Imagine if you couldn’t COMMIT if GitHub was offline.
But in a (someday, maybe) future where code changes 1000x per day with no human in the loop, then your VCS is basically part of production anyway, so you might as well lean into keeping it online with a team of SREs etc, and then you get all sorts of interesting perf benefits for CLIENTS because you can offload some processing to server and re architect what all needs to be stored where
* I’m not sure I buy this, but the labs are certainly pushing “don’t read the code, leverage signals like “outage, feature request, user behavior change” as STIMULUS to agents to drive change in deployed code” as the future, so it lines up
Does that make sense? Are we going back to CVS instead of distributed? Will there be another swing back to distributed 5-10 years after things like Scion become Mainstream?