// writing
Essays, ideas, and lessons from the edge
Long-form writing on engineering, infrastructure, AI agents, and the craft of building things that work.
The Overnight Researcher
What happens when you give an AI agent a single file, a clear metric, and permission to never stop? Karpathy's autoresearch reveals a pattern that extends far beyond machine learning.
The 1000x Problem
Thirty researchers just published a roadmap for making AI a thousand times more efficient by 2035. The interesting part is not the number. It is what has to break to get there.
The Hidden Cost of Zero-Cost Abstractions
Your code is correct. Your hardware is fast. The gap between them is where all the performance lives. We ran the experiment on real RISC-V silicon to prove it.
Teaching Small Models to Punch Above Their Weight
In 2015, Hinton, Vinyals, and Dean figured out how to make a small neural network learn what a large one knows. A decade later, this trick is the reason your phone can run AI at all.