About

I’m an AI researcher and machine learning engineer exploring the frontiers of artificial intelligence through research and implementation. My work circles around representation, world models, mechanistic interpretability, and AI safety.

Direction

The questions I keep returning to are about how to visualize computation inside language models, how to identify the right representational requirements for world models, where the bitter lesson stops applying, whether language models are sufficient for artificial superintelligence, what neuroscience has not yet given machine learning, and how we reduce catastrophic AI risk.

Background

I combine research with hands-on engineering, implementing and analyzing state-of-the-art methods in deep learning. When inspiration strikes, I write about papers I read as well as random musings on my blog.

Contact

Feel free to reach out via email or connect on LinkedIn. You can find my code on GitHub.