Agent output is already sorting itself by framework. amplifying's september sample shows react and…
agent output is already sorting itself by framework. amplifying's september sample shows react and next.js pulling more work than the next ten frameworks combined, devin leading angular at 50.9% and rails at 32%, and the copilot agent leading .net at 48.8%.
the agent you adopt quietly picks your framework for you.
Context
Amplifying publishes a live page on which coding agents work on which frameworks, with a sample window of 7 to 27 September 2026, later than the note's date. In the copy read, React and Next.js are each 17 percent of framework volume, Devin leads Spring at 67 percent, the Copilot agent leads .NET at 43 percent, Devin leads Angular at 47 percent on 91 sampled pull requests and Rails at 25 percent on 28, which the page calls a rough sketch. Only 6.6 percent of sampled pull requests matched a framework, and the page says equal-size samples per agent show a portfolio tilt, not market share.
The note's 50.9, 32 and 48.8 percent do not appear in the current page, which covers a different window; that is a different window and not a refutation, and the earlier snapshot was not recoverable. More work than the next ten frameworks combined was not supported by the current page, where the two are 34 percent and the next ten sum to about 53 percent; whether the earlier window differed was not checked. The shares are each agent's share of its own equal-size sample over matched pull requests only. The claim that the agent you adopt picks your framework is the author's causal reading: the data shows where each agent's sampled work concentrates, not anyone's choice.
Watch next
- A dated snapshot of the earlier window and per-framework sample sizes.
Sources
- Coding agents by framework (Amplifying)amplifying.ai
- Angular segment (Amplifying)amplifying.ai
- Rails segment (Amplifying)amplifying.ai
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 03:42 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 →