Just shipped a build with agents fully banned from touching the test file. same task, 9 hours, 2.1M…
just shipped a build with agents fully banned from touching the test file. same task, 9 hours, 2.1M tokens, cost dropped 38% and the tests actually pass on first run now.
ryanvogel was right.
Context
Anthropic's post on building effective agents covers testing and evaluation inside agent loops and recommends simple, composable patterns. METR's early-2025 study found experienced open-source developers took 19 percent longer with AI tools in that setting.
The build, the 9 hours, 2.1M tokens and 38 percent cost drop are the author's own measurements, and I inspected no evidence for them. Neither source above says anything about banning agents from test files, and the ryanvogel reference is not identified.
Watch next
- Whoever ryanvogel refers to, if the author names the source.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 3 September 2026 at 21:01 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 →