Karpathy proposes replacing on-the-fly retrieval with an LLM-maintained markdown wiki that ingests sources, compiles structured pages, and self-updates through ingest, query, and lint cycles. This approach builds a persistent, compounding knowledge base without vectors or re-retrieval, though it currently lacks enterprise controls.

Nick Spisak outlines a straightforward method to create a personal knowledge base using simple folder structures and AI tools. He emphasizes the importance of dumping all notes into one place and automating organization and updates through a schema file and web scraping.