Weeknotes: F1 Data Analysis, and an Autonomous Agent Called Gravel
F1 is in full swing now and the F1 Picks 2026 prediction game has become a testing ground for two different ways of working with agents.
Dylan Patel — Deep dive on the 3 big bottlenecks to scaling AI compute
dwarkesh.comPlus, why an H100 is worth more today than 3 years ago
Weeknotes: Going Deeper on LLMs, Marginalia, and Agent Toolkit Skills
This week I’ve been going deeper on how LLMs actually work - not just using them, but trying to understand what’s happening under the hood. This has led me to build a reading companion app to assist in learning.
On Hormuz (and concretely leveraging geography)
Compacted Context — Dylan Martin's website, where I publish essays about software engineering, career reflections, or whatever else I'm thinking about, as well as digests of what I'm reading or watching.
So, About That AI Bubble
Thanks to the rise of Claude Code and other AI agents, revenues are finally catching up to the hype.
The Centaur Era
The question isn't what AI can do, it's what you can do with AI