Andrej Karpathy
Person
From 2011 to 2015 Andrej Karpathy did his PhD at Stanford University, where he designed the CS231n course and taught most of it. He was a founding member of OpenAI and worked there as a research scientist from 2015 to 2017. From 2017 to 2022 he was director of AI at Tesla, where he led the computer vision team for Autopilot. He was back at OpenAI from 2023 to 2024.
In April 2026 he published a short piece called “LLM Wiki”, which describes how a language model can take over the job of keeping personal notes organised.
In my articles
In my second brain series, I explain Karpathy’s pattern, in which a language model maintains a wiki, with an example from sales: the model reads each transcript once, right after the meeting, and adds the agreed points to the client’s page. The note in which he describes the pattern has its own entry, “LLM Wiki”.
Sources
Related articles
Related entries
Last checked:
All entriesLLM (large language model)
An LLM, or large language model, is a program that has been trained on vast amounts of text and can generate answers and other writing.
LLM Wiki
“LLM Wiki” is a short note by Andrej Karpathy from April 2026. It describes a pattern in which a language model builds and maintains a wiki of Markdown files.