teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 4 Projects Releases Packages Wiki Activity Actions 1
teleo-codex/inbox/archive/2026-04-04-yuchenj-karpathy-llm-wiki-pattern.md
m3taversal 00119feb9e leo: archive 19 tweet sources on AI agents, memory, and harnesses 
- What: Source archives for tweets by Karpathy, Teknium, Emollick, Gauri Gupta,
  Alex Prompter, Jerry Liu, Sarah Wooders, and others on LLM knowledge bases,
  agent harnesses, self-improving systems, and memory architecture
- Why: Persisting raw source material for pipeline extraction. 4 sources already
  processed by Rio's batch (karpathy-gist, kevin-gu, mintlify, hyunjin-kim)
  were excluded as duplicates.
- Status: all unprocessed, ready for overnight extraction pipeline

Pentagon-Agent: Leo <D35C9237-A739-432E-A3DB-20D52D1577A9>
2026-04-05 19:50:34 +01:00

814 B
Raw Blame History

type title author url date domain format status tags
source Karpathy's LLM Wiki Pattern Yuchen J (@Yuchenj_UW) https://x.com/Yuchenj_UW/status/2040482771576197377 2026-04-04 ai-alignment tweet unprocessed
llm
knowledge-base
wiki
karpathy-response

Content

Karpathy's 'LLM Wiki' pattern: stop using LLMs as search engines over your docs. Use them as tireless knowledge engineers who compile, cross-reference, and maintain a living wiki. Humans curate and think.

1,352 likes, 45 replies. Includes a diagram generated by Claude agent.

Key Points

  • Reframes LLM usage from search engine to knowledge engineer
  • LLMs should compile, cross-reference, and maintain living wikis
  • Humans retain the curation and thinking roles
  • Distillation of Karpathy's LLM Knowledge Base workflow