LLM as Knowledge Worker

Core Idea

LLMs are uniquely suited to the grunt work of knowledge management: summarizing, cross-referencing, filing, bookkeeping, consistency checking. Humans abandon wikis because maintenance burden grows faster than value. LLMs don’t get bored, don’t forget to update a cross-reference, and can touch 15 files in one pass.

The Division of Labor

Role	Human	LLM
Source curation	✅ Decides what to read	❌
Asking questions	✅ Directs inquiry	❌
Making meaning	✅ Interprets, decides	🔶 Assists
Summarizing	❌	✅
Cross-referencing	❌	✅
Contradiction detection	❌	✅
Filing & organizing	❌	✅
Keeping pages current	❌	✅

Karpathy’s framing: “Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase.”

Implications

• This isn’t “AI replacing humans” — it’s AI handling the part humans consistently fail at (maintenance)
• The human’s judgment is more valuable, not less, because they’re freed from bookkeeping
• Quality depends on the schema/conventions — the LLM needs clear instructions on how to maintain

Connections

• Karpathy LLM Wiki Pattern
• Compounding Knowledge