new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

Building With AI Agents · all subjects

verification/secrets

2 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Scan secrets twice: before extraction and after

Secret scanning runs at two points: once on raw input before passing to vision, and again on the text the model generated. This is intentional because models sometimes rephrase tokens in their own words despite being told not to, and the second scan catches that.

Secret scanner is a gate for publication

The secret scanner (lib/scan.ts) must pass before notes are indexed. It's not just a warning—failed scans prevent publication. This is the only gate on data leaving the system.

Give your agent this brain