LLM Knowledge Bases — using LLMs to build personal knowledge bases
Highlights
- ▸At ~100 articles / ~400K words, plain LLM-read-the-wiki beats RAG — index files and doc summaries the LLM maintains itself are enough
- ▸The LLM writes and edits the wiki; the human rarely touches it, breaking the assumption that knowledge bases need human-authored notes
- ▸Outputs (slides, images, markdown) get filed back into the wiki, so every query compounds the knowledge base instead of being thrown away
Original excerpt
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts,…
Frequently asked questions
What is "LLM Knowledge Bases — using LLMs to build personal knowledge bases" about?
This article by Andrej Karpathy is part of the Andrej Karpathy reading list on Burn 451, covering ai agents.
Who wrote "LLM Knowledge Bases — using LLMs to build personal knowledge bases"?
This piece is part of the Andrej Karpathy vault on Burn 451, covering ai agents. The original author is attributed at the source link.
How can I read more content from Andrej Karpathy?
The complete Andrej Karpathy reading list is available at burn451.cloud/vault/karpathy. Each article includes an AI-generated summary so you can decide what to read in seconds. Connect the Burn 451 MCP server to Claude or Cursor to query all Andrej Karpathy articles as live AI context.
Can I use "LLM Knowledge Bases — using LLMs to build personal knowledge bases" with Claude or Cursor?
Yes. Install the burn-mcp-server npm package and connect it to Claude Desktop, Claude Code, or Cursor. Once connected, your AI can search and reference this article and the full Andrej Karpathy vault in real time — no manual copy-paste required.
37 more articles in this vault.
Import the full Andrej Karpathy vault to Burn 451 and build your own knowledge base.
Content attributed to the original author. Burn 451 curates publicly available writing as a reading index. For removal requests, contact @hawking520.