Hi, my name is Dylan. I’m a research scientist at Assured Information Security where I conduct deep learning research for the U.S. military. Prior to this, I graduated from the University of Illinois in 2023 with a degree in mathematics and computer science.
I also moonlight as an AI alignment researcher. I'm currently an independent collaborator and tech lead with Prof. Daniel Kang's lab working on a large safety evaluation suite for AI agents. Prior to this, I messed around with some stuff in mechanistic interpretability and computational mechanics and ran some alignment programming for my university's effective altruism club.