Andrej Karpathy on X: "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" / X
To view keyboard shortcuts, press question mark View keyboard shortcuts Home Explore Notifications Chat Grok Premium Bookmarks Creator Studio Articles Profile More Post Lydia (in SF) @LydNot Post See new posts Conversation Andrej Karpathy @karpathy 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, writes articles for them, and links them all. To co
@karpathy: 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 structur
saved by
related reading
- llm-wikigist.github.com
- Deep Dive into LLMs like ChatGPTyoutube.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- Here’s how I use LLMs to help me write codesimonwillison.net
- GitHub - nashsu/llm_wiki: LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。github.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- Customizing Karpathy's LLM wiki for fighting diseasekamens.com
- Malleable software in the age of LLMsgeoffreylitt.com
- Productizing Large Language Modelsblog.replit.com
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
- Taking LLMs Seriously (As Language Models) — LessWronglesswrong.com