The Karpathy LLM wiki method has near-zero cost (only token costs for querying) versus traditional RAG which incurs ongoing compute and storage expenses.

factualpending

Speaker

Unidentified Speaker — Andrej Karpathy Just 10x’d Everyone’s Claude Code [sboNwYmH3AY]

Evidence Quote

“The cost over here is basically free. Your only cost is going to be tokens. Whereas, over here you might have ongoing compute and storage.”

Source

Andrej Karpathy Just 10x’d Everyone’s Claude Code— Nate Herk | AI Automation
Created: 8/13/2026, 7:48:45 AM

Your notes

Loading notes...