Field notes
Short essays on the problems we work on, the choices behind our tools and what we are still unsure about.
All notes
-
Unknown should stay unknown
Tools that report on AI agents are tempted to round thin evidence up into confident statements. We think the labels matter more than the summary.
-
What a test run can and cannot say about a patch
A green test suite tells you the patch passes. It does not tell you which parts of the patch the tests depend on. Counterfactual runs can.