Anthropic's ci load grew 25x in six months after claude started writing most of the code, and the…
anthropic's ci load grew 25x in six months after claude started writing most of the code, and the singleton test-history writer became the single point of failure. the agent boom doesn't end at codegen.
the next bottleneck is your build pipeline.
Context
Anthropic's post of 14 September 2026 says its CI job volume increased 25x over 6 months and that it patched its test selection service three times. It says engineers ship on average 8x as much code per quarter as in 2021-2025, Claude authors 80% of that code, and tests across the codebase grew 10x with a nominal increase in engineers. The v0 design ran as a single process because a single writer applied results to keep per-test history, which prevented horizontal sharding. The fix moved results to an in-memory store with a journal and a small consumer.
The 25x is CI job volume, not compute or cost. The post attributes the rise to 8x code per engineer plus 10x tests, so after Claude started writing most of the code is only partly the post's causal claim. Single point of failure is the note's gloss on the post's scaling limit. Vendor first-party account, not independently audited.
Related work
- Anthropic CI test impact analysis (clauding.de) ↗Secondary, snippet only.
Watch next
- Anthropic's follow-up numbers on the new design.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 11:05 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →