BREAKING
Karpathy's LLM Wiki Goes Viral
LLM Wiki vs Classic RAG
RAG
old way
●
Re-retrieves chunks each query
●
No knowledge accumulation
LLM Wiki
new way
●
Compiles sources once
●
Knowledge compounds over time
Three Core Operations
1
Ingest sources
↓
2
Query and answer
↓
3
Lint contradictions
Three-Layer Structure
1
Raw sources
↓
2
Wiki (LLM-built)
↓
3
Schema / CLAUDE.md
Praise and Limits
Upsides
●
Setup in 5 to 15 minutes
●
Maintenance nearly zero
Limits
●
index.md fails past 100 articles
●
Tokens and hallucination risk
A Local RAG-Free Alternative
AI NEWS BLITZ
Andrej Karpathy's LLM Wiki pattern turns an Obsidian vault into a self-updating knowledge base.