LLM Wiki
HumanKarpathy’s pattern: LLMs compile raw sources into a persistent interlinked markdown wiki—entity/concept pages, index, log—rather than re-deriving answers from RAG on every query.
Knowledge catalogue
Karpathy’s pattern: LLMs compile raw sources into a persistent interlinked markdown wiki—entity/concept pages, index, log—rather than re-deriving answers from RAG on every query.
Apple paper: keep specs, schemas, tool config, and constraints; drop session traces. Selective shared memory beat both no memory and full history.