BREAKING
Karpathy Publishes "LLM-Wiki" Pattern
How LLM-Wiki Works
1Raw sources kept immutable
2LLM agent extracts entities
3Builds linked wiki
4Knowledge compounds
RAG vs LLM-Wiki
RAG
Re-synthesizes per query
Temporary knowledge
Hard to compound
LLM-Wiki
Uses compiled wiki
Persistent and structured
Grows in value over time
Obsidian as the IDE
0+
pages converted
A Free, Open Knowledge Pattern
AI NEWS BLITZ
Andrej Karpathy has shared a new design pattern for building persistent AI knowledge bases.