https://aiforhumanexpertise.com/tags/llm-wiki/Recent content in Llm-Wiki on AI For Human ExpertiseHugoen-gbSun, 05 Apr 2026 00:00:00 +0000https://aiforhumanexpertise.com/blog/llm-wiki-smarter-knowledge-bases/Sun, 05 Apr 2026 00:00:00 +0000https://aiforhumanexpertise.com/blog/llm-wiki-smarter-knowledge-bases/<h2 id="a-better-pattern-for-organisational-knowledge">A Better Pattern for Organisational Knowledge</h2> <p>Andrej Karpathy - the AI researcher known for his work at OpenAI and Tesla - recently shared a pattern he calls the &ldquo;<a href="https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f">LLM Wiki</a>.&rdquo; It addresses a fundamental limitation in how most organisations use large language models for knowledge work today.</p> <p>The standard approach is retrieval-augmented generation (RAG): upload documents, the AI retrieves relevant chunks at query time, and generates an answer. It powers tools like ChatGPT file uploads and most enterprise search products. It works - but nothing accumulates. Every question forces the AI to rediscover knowledge from scratch, piecing together fragments across documents each time.</p>