Karpathy Left His GPU Running Overnight. The Agent Found a Bug Everyone Missed for Months.

Towards AI
Machine Learning AI Hardware AI Research

“The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement.” - Andrej Karpathy, March 2026. My first reaction was: that sounds like a job posting for a system that replaces me. Then I actually ran it. I Have Wasted a Lot of GPU Hours Doing What an Agent Can Do Better I have run hundreds of ML experiments the manual way. Edit a file. Kick off a run. Wait. Check the loss curve. Feel vaguely disappointed. Edit a slightly different file. Repeat until midnight.