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

deploy/resources

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

Container memory limits must account for actual model sizes, not assumptions

A comment assumed bge-m3 was ~2 GB, but it was actually 3.0 GB of a 4 GB limit. Downloading the reranker weights would have OOM-killed the embed container, taking search and ingest down together. Limits should be runaway guards rather than budgets. With models that vary, verify against actual files and set the limit well above.

Give your agent this brain