The 'LLM Wiki' Pattern: Stop Using Language Models as Search Engines

A visualization of Karpathy's 'LLM Wiki' concept — built by a Claude agent — is gaining traction as developers rethink how to structure AI-powered knowledge retrieval.

A concept originally floated by Andrej Karpathy is getting fresh attention through an agent-built diagram. As @Yuchenj_UW shared, the "LLM Wiki" pattern argues that using language models as search engines is a misuse of their capabilities. Instead, the pattern proposes structuring knowledge retrieval so the LLM acts as an editor and synthesizer of curated, versioned knowledge — more like a wiki that writes itself than a search bar that hallucinates.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief