Claude now writes code so fast that Anthropic had to rip out git, the tool basically every software company on Earth uses to track changes to its code. Back in May, Anthropic was merging about 2,500 code changes a day. By September it was over 30,000. That's one every three seconds, all day and all night, with Claude driving most of the increase. Git was never built for that. It was designed in 2005 so every developer's copy of a project carries the full history and works offline. That's great if you're a person coding on a plane. Anthropic's main code history is now almost 100 GB, their test systems pull a copy of the code 25 million times a day, and nearly all of those requests come from AI agents and automated jobs that are always connected anyway. Done the normal git way, that adds…Read original on X
StoryFirst seen
Anthropic replaces git as agent-written code overwhelms merging
When agents merge code every few seconds, version control becomes the next bottleneck for engineering organizations everywhere.
Everything it touches
4 names 4 voices 4 source posts
The story’s neighborhood
Explore the graph, or choose a connection below.
Follow the evidence
The source posts
This brief comes from Tech Twitter’s edited headlines. The posts below are the sources grouped with the story; statements in them belong to their authors.
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:Read original on X
SITUATION DETECTED: Anthropic says its code merges per day have grown tenfold and Claude is now able to autonomously iterate on research loops at a speed and scale they have not seen before.Read original on X
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…Read original on X
How the headline evolved
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git as agent-written code overwhelms merging
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Anthropic replaces git to handle agent-scale code merges
Shared connections
Related stories
Mathematicians scramble to digest OpenAI's breakthrough results
Researchers including Scott Aaronson describe colleagues dropping their work to unpack AI solutions to problems that stood open for decades.
OpenAI claims breakthroughs on famous unsolved math problems
Mathematicians including former OpenAI researcher Scott Aaronson say colleagues across the field are dropping their work to verify results that crack decades-old open problems, and
Anthropic drafts frontier AI bill to take to lawmakers
A leading lab writing its own proposed rules for frontier AI and taking them to lawmakers marks a new phase in industry self-regulation.
ElorianAI launches Glimpse vision model for spatial reasoning
Early side-by-side tests show the model, built by veterans of Google and Apple vision work, outscoring a rival on spatial tasks at low per-token prices.