Claim◆Article · 3:00 — 5:00

Using LLMs to build personal knowledge bases is the single most useful productivity improvement I tried this year.

The author built an LLM wiki after seeing Karpathy's tweet describing the concept, and found it to be the most impactful productivity change he made all year. ✦ AI generated

Casey Newton · Platformer · 2026-08-19 · original ↗

Share card ↓Export .md Export .txt

As it so happens, it has. Of everything I tried this year to get better at the deskbound parts of my job, the LLM wiki has easily been the most useful. Like a vintage sports car, it requires a fair degree of maintenance, and there are almost certainly easier ways to create a personal knowledge base. But if you do any sort of work that has made you crave the help of a good research assistant, an LLM wiki might be worth your time.

Read full article ↗excerpt · fair-use quotation

✳ LLM wiki ◉ Andrej Karpathy

Around this claim

This moment responds to

gives example → The LLM wiki automates my old blips system—each morning it generates new pages for concepts in the news and updates a home page highlighting current stories, which directly generates podcast segments and story ideas.Casey Newton · Platformer rebuts → Today's LLMs increase entropy rather than compressing and organizing knowledge in long-form nonfiction, so they will remain dependent on human guidance.the author · Interconnects explains mechanism → The wiki is useful for fast-evolving, complex stories because it compiles detailed timelines with original sources, letting me quickly refresh my memory while verifying nothing was hallucinated.Casey Newton · Platformer rebuts → LLMs are good at checking or producing individual components and making small edits, but they compound errors when asked to organize and connect those components into an entire technical chapter.the author · Interconnects