Andrej Karpathy and Aakash Gupta describe using LLMs to compile personal knowledge bases from raw sources into linked markdown wikis, while Fraser Cottrell frames a Claude plus Obsidian setup as an always available research assistant.
using LLMs to build personal knowledge bases for various topics of research interest.
dump raw sources into a folder, let the LLM compile a markdown wiki, maintain all the links, run data quality checks, and answer complex questions across 400K words.
This is my full Claude + Obsidian system. Literally feels like I have an employee who knows everything about everything.
LLM Knowledge Bases
using LLMs to build personal knowledge bases for various topics of research interest
a large fraction of my recent token throughput is going less into manipulating code
This finding is one of many signals tracked across Indiehacking. The live feed updates every few hours with new expert voices, debates, and emerging ideas.
← Back to Indiehacking