From 44985f7391264f03730df7644d0d180809e3a33c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pawe=C5=82=20Doma=C5=84ski?= Date: Tue, 9 Jun 2026 13:39:36 +0000 Subject: [PATCH] Jun 9, 2026, 3:39 PM --- brain/GEMINI.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/brain/GEMINI.md b/brain/GEMINI.md index e15aa46..515fe62 100644 --- a/brain/GEMINI.md +++ b/brain/GEMINI.md @@ -95,9 +95,10 @@ You drop a new source into the raw collection and tell the LLM to process it. An 4. **Feynman Check**: Compare against `knowledge/feynman_problems.md` and update it if connections are found. 5. Create/Update concept and entity pages across the knowledge base using the required sections. A single source might touch 10-15 knowledge base pages. 6. Add cross-links in both directions between all touched pages. -7. Update `knowledge/log.md` and relevant indices in `knowledge/indices/`. -8. Update `knowledge/index.md` if new categories are needed. -9. Flag any contradictions with existing content. +7. closs-link any knowledge/wiki pages generated or updated to the roginal source page. +8. Update `knowledge/log.md` and relevant indices in `knowledge/indices/`. +9. Update `knowledge/index.md` if new categories are needed. +10. Flag any contradictions with existing content. *Personally I prefer to ingest sources one at a time and stay involved — I read the summaries, check the updates, and guide the LLM on what to emphasize. But you could also batch-ingest many sources at once with less supervision.*