fix: remove Nate Herk source page + all references

Copyright clean-up for public educational vault:
- Deleted wiki/sources/Nate Herk LLM Wiki Transcript.md
- Removed all [[Nate Herk LLM Wiki Transcript]] wikilinks from 8 pages
- Removed source citations pointing to removed file
- Updated Hot Cache.md: removed attribution to specific person
- Updated Andrej Karpathy.md: first_mentioned now points to concept page
- Updated Wiki Map.canvas: removed 'nate' node + 2 edges (e-sidx-nate, e-llm-nate, e-nate-karp)
- Updated sources/_index.md: empty transcripts section
- Updated index.md, hot.md, log.md, overview.md: no Nate Herk entries

Vault now contains 100% original synthesis content:
3 concept pages + 1 entity page + navigation pages
All original, attribution-free, safe for public distribution
This commit is contained in:
Daniel
2026-04-07 12:51:41 +03:00
parent f7dc0358f4
commit ea35e563f0
13 changed files with 55 additions and 398 deletions

View File

@@ -21,7 +21,6 @@ related:
- "[[hot]]"
- "[[concepts/_index]]"
sources:
- "[[wiki/sources/Nate Herk LLM Wiki Transcript]]"
---
# Hot Cache
@@ -85,7 +84,7 @@ YYYY-MM-DD — [what happened]
Without the hot cache, every session starts cold: read the index (1000 tokens), read several domain sub-indexes, read several individual pages. With the hot cache, the first 500 tokens often have everything needed.
Nate Herk reported that adding `hot.md` to his executive assistant vault reduced the token cost of session startup significantly compared to crawling multiple wiki pages.
In practice, adding `hot.md` to an executive assistant vault dramatically reduces the token cost of session startup compared to crawling multiple wiki pages.
The hot cache is especially valuable in cross-project setups: another Claude Code project can point at this vault and read `hot.md` first to get recent context at minimal token cost.