XFollowList Find a person
Andrej Karpathy’s avatar

Andrej Karpathy

AI researcher and educator

Explains how language models change software development, from his original description of vibe coding to experiments where an agent changes training code and measures the result.

@karpathy on X

Community rating

87

Vote once every 24 hours. No account needed.

Why read Andrej Karpathy?

Start with Karpathy to understand what building through conversation means. His original vibe coding post describes asking a model for changes while letting the code recede from view. It gives you a reference point for a term now used for many different AI workflows.

His autoresearch repository makes an agent's work concrete: change one training file, run an experiment, measure it, then keep or discard the change. For readers arriving from crypto, his Bitcoin tutorial offers the same approach to understanding a system by constructing its parts, including keys, signatures and a transaction.

For the models behind coding agents, his Zero to Hero course connects small neural networks to a GPT implementation. Follow the earlier language-modeling and PyTorch lessons before the Transformer lecture.

Selected work

  1. Post,

    What does building through conversation look like? Karpathy describes a workflow in which spoken requests drive changes and the developer stops focusing on the code itself.

    Cite this selection

    XFollowList, “Vibe coding: the original description” reading notes in the Andrej Karpathy profile. https://xfollowlist.com/people/andrej-karpathy#work-4c5503150173

    The linked work is the original source; this permalink identifies XFollowList’s reason to read it. Original work published .

    Profile-source checking date and references · Dated reading map

  2. Code

    How can an agent evaluate its own changes? Read the README and program.md to see a small experiment loop with one editable training file, a fixed time budget and a measured result.

    Cite this selection

    XFollowList, “autoresearch: agents running training experiments” reading notes in the Andrej Karpathy profile. https://xfollowlist.com/people/andrej-karpathy#work-f226959a357f

    The linked work is the original source; this permalink identifies XFollowList’s reason to read it. Original publication date is unknown.

    Profile-source checking date and references · Dated reading map

  3. Tutorial,

    What is inside a Bitcoin transaction? This educational walkthrough builds keys, addresses, signatures and a testnet transaction in Python, connecting the cryptography to the data that moves through the network.

    Cite this selection

    XFollowList, “A from-scratch tour of Bitcoin in Python” reading notes in the Andrej Karpathy profile. https://xfollowlist.com/people/andrej-karpathy#work-12faa11def50

    The linked work is the original source; this permalink identifies XFollowList’s reason to read it. Original work published .

    Profile-source checking date and references · Dated reading map

  4. Course

    How do neural networks become language models? Karpathy’s course builds from backpropagation to GPT and tokenization. It asks for solid Python and introductory calculus; use the earlier lessons before the GPT implementation.

    Cite this selection

    XFollowList, “Neural Networks: Zero to Hero” reading notes in the Andrej Karpathy profile. https://xfollowlist.com/people/andrej-karpathy#work-199fdd6cb1c5

    The linked work is the original source; this permalink identifies XFollowList’s reason to read it. Original publication date is unknown.

    Profile-source checking date and references · Dated reading map

Projects & roles

  • autoresearch

    A small training setup for experimenting with agents that modify code and compare results.

  • micrograd

    A compact automatic differentiation engine and neural network library for learning the mechanics of training.

Sources & further reading

Profile sources checked . This describes checking these references, separately from the publication dates of selected works.

Cite this profile’s source check

XFollowList, Andrej Karpathy profile sources. Sources checked 2026-10-09. https://xfollowlist.com/people/andrej-karpathy#sources-checked