blog
thoughts, tutorials, and musings
Note (April 28, 2026): I'll now be sharing my latest work and thoughts on Substack. Subscribe if you find my posts useful. The blog posts below remain archived here.
-
Architecture Shapes Thought
Why the path to robust AI reasoning probably requires building cognition in, not scaling it up.
-
When LLMs Play Games: The Cooperation Secret
What happens when language models face the Prisoner's Dilemma?
-
Your AI Knows More Than It Can Do
Understanding the systematic gap between what language models can describe and what they can actually do
-
The Car Wash Problem: When LLMs miss the obvious
Exploring how LLMs fail at pragmatic reasoning and why this matters for AI safety
-
Isn't Deactivating Neurons So Good?
Conducting ablation experiments in neural networks