ea35e563f0
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
1.7 KiB
type, title, entity_type, role, first_mentioned, created, updated, tags, status, related, sources
| type | title | entity_type | role | first_mentioned | created | updated | tags | status | related | sources | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| entity | Andrej Karpathy | person | AI researcher, educator, founder | LLM Wiki Pattern | 2026-04-07 | 2026-04-07 |
|
mature |
|
Andrej Karpathy
AI researcher and educator. Former Director of AI at Tesla, founding member of OpenAI. Known for deep learning education (Neural Networks: Zero to Hero series, micrograd, nanoGPT) and for publishing practical AI patterns.
Key Contributions to This Wiki
Karpathy originated the LLM Wiki Pattern — the idea of using LLMs to build and maintain a persistent, compounding knowledge base rather than re-deriving knowledge from raw documents on every query.
He published the idea as an "idea file" — intentionally abstract, designed to be copy-pasted into a Claude Code or similar session and built out collaboratively. The cosmic-brain plugin is a production implementation of this pattern.
His framing: "The wiki is a persistent, compounding artifact. The cross-references are already there. The contradictions have already been flagged. The synthesis already reflects everything you've read."
Notable Quote
"I thought that I had to reach for fancy RAG, but the LLM has been pretty good at auto-maintaining index files and brief summaries of all documents and reads all the important related data fairly easily at this small scale."
Connections
- LLM Wiki Pattern — his core contribution to knowledge management
- Compounding Knowledge — the central insight he articulated
- cosmic-brain plugin — this repo is a production implementation of his pattern