AI · Official
Anthropic Rebuilds Its Source Code Management System to Keep Up with AI Coding
Anthropic Engineering (mirror) ·
At a glance
Anthropic said AI has greatly sped up code writing, making its existing development tools a bottleneck. Inside the company, it built a new version control system called Scion and moved a large repository to it. The article explains the background and design thinking behind this work.
Key points
- As AI wrote code faster, the number of code merges rose from about 2,500 per day in May 2026 to more than 30,000 per day in September.
- The company says it moved its repository from git to Scion in five months.
- Git gives each person a full copy and lets them work offline, but for AI agents that are always online, this design got in the way of scaling.
- The existing workarounds, such as multiple internal replicas and partial clones, became hard to manage as the repository grew.
Why it matters
It is an example of how development tools may need to change in an era when AI produces code in large volumes.
Original source
Redesigning source control at Anthropic
Anthropic Engineering (mirror) · Oct 13, 09:00 KST
Read on Anthropic Engineering (mirror) ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to Anthropic Engineering (mirror).
More from this field
- AWS Quick Adds Chat-Built Flows, Updated Web App, and Teamwork Among Agents
AWS Quick added updates that let a team turn one person's work routine into a shared, repeatable process. Flows can now be built and changed entirely in chat, and they can run from the web, desktop, or mobile app. Agents working together can also give more complete answers.
Amazon AWS Machine Learning blog · Nov 21, 10:06 KST - Amazon Bedrock Web Search Adds Five Languages and Country-Based Results
Amazon's Web Search tool for Bedrock, which gives AI agents cited, up-to-date web results, now supports Spanish, French, German, Italian, and Japanese, plus non-US English. A new optional country field can also steer results toward sources from a specific country. Existing customers get the language update automatically, and pricing stays the same in every language.
AWS What's New · Nov 21, 09:17 KST - AWS Adds Shared Cache Skill to Cut Self-Hosted LLM Cost and Latency
AWS wrote about a shared cache that lets self-hosted AI models reuse saved work across servers, aiming to cut cost and wait time. The post shows how a coding agent can help set it up. Amazon says it can cut inference cost by up to 40% and first-token delay by up to 80%.
Amazon AWS Machine Learning blog · Nov 21, 09:14 KST - Can AI Really Find Black Friday TV Deals? A BBC Test Says Not Yet
A BBC team tested four popular AI chatbots to see if they could find a good Black Friday deal on a 55-inch TV. The results were mixed, with many links broken or out of date.
BBC News · Nov 21, 09:06 KST