About Me

I'm a Machine Learning Engineer, deep learning enthusiast, Interpretability & RL fan. Most days I'm working Mechanistic Interpretability, and lately training models to do useful things. Currently deep in mechanistic interpretability, and many other things. I think a lot about alignment, Reinforcement Learning, and what intelligence actually means.

Research Domains

Core Research

Mechanistic Interpretability
Inference Optimization
RLVR
AI Alignment

Current Goals

Large Language Models
Reinforcement Learning
CUDA Programming
Vision Models (eg. Diffusion, YOLO, SAM)

GitHub Activity

Loading contributions...

Interactive Playground

A little cellular automata simulation to play with. Adjust the parameters to see how the system evolves.

Game of Life

Click cells to toggle. Conway's classic.

Gen: 0