## 100K people bookmarked @karpathy's

View Tweet

:

Then he dropped a full GitHub Gist. 5,000+ stars. 1,400+ forks. Two days.

Most people will bookmark that too. Then do nothing.

Not because it's hard. Because nobody gave them the exact prompts.

I'm going to fix that.

I'll walk you through the full system, hand you copy-paste prompts for every step, and tell you where this breaks so you don't waste a weekend on something that falls apart at scale.

---

"The human's job is to curate sources, direct the analysis, ask good questions, and think about what it all means. The LLM's job is everything else." — Andrej Karpathy

---

## The Concept (60-Second Version)

You have knowledge scattered everywhere. Articles saved in 4 apps. Bookmarks from 2023 you'll never revisit. Notes from meetings that live in a folder you forgot existed.

Right now, when you ask AI a question about your stuff, it starts from zero every time. Upload docs, ask a question, get an answer. Next session? It's forgotten everything. That's how ChatGPT file uploads, NotebookLM, and most RAG systems work. Zero accumulation.

Karpathy's idea flips this.

Instead of the AI searching your raw files every time, the AI reads your sources once and compiles a structured wiki. Summaries, cross-references, connections between ideas, contradictions flagged.

All maintained by the AI. All in simple markdown files.

Next time you ask a question, the AI doesn't dig through raw documents. It reads the wiki it already built.

The connections are already there.

The synthesis already reflects everything you've read.

Every new source you add makes the wiki richer. Every question you ask can get filed back in. Knowledge compounds instead of resetting.