Karpathy’s autoresearch could make scientists of us all

Karpathy’s autoresearch could make scientists of us all

From Azeem Azhar's Exponential View by Azeem Azhar

April 1, 2026 · 21 min · Episode 39

About this episode

Azeem Azhar explores how Andrej Karpathy's autoresearch AI tool can be adapted for various problem-solving applications beyond machine learning.

Published in early March 2026, Andrej Karpathy's autoresearch AI tool makes autonomous scientific experimentation cheap and easy — but it was designed to solve machine learning problems. I wanted to see if I could apply its loop architecture to my own work: refining my worldview, testing arguments, solving business problems. In this video, I share how I adapted Karpathy’s autoresearch loops for problems that aren't easy to quantify, how to avoid the local minima trap, and the broader impact of these kinds of methods. I covered:

Topics covered

  • technology
  • business
  • investing
  • science
  • AI

Keywords

  • autonomous scientific experimentation
  • autoresearch AI tool
  • machine learning problems
  • refining worldview
  • testing arguments
  • solving business problems
  • local minima trap
  • impact of methods

Mentioned in this episode

Products: Karpathy’s autoresearch

More episodes of Azeem Azhar's Exponential View

Explore listener stats, chart rankings, contacts and more on the Azeem Azhar's Exponential View podcast page.