Writing
-
Reverse Engineering Catan Universe Gameplay with Large Language Models
-
Notes on RL Environments
-
Verification Unlocks Automation
-
Memory is Abstraction + RL: LLMs Need to Learn Like Humans
-
AI in Anti-Inductive Domains
-
The Bitter Lesson: Rethinking How We Build AI Systems
-
Lessons from Deepseek
-
RL was not priced in
-
Small Bets about AI
-
Hello World
subscribe via RSS