Subhash KANTAMNENI

Subhash Kantamneni is a Master’s student in Electrical Engineering and Computer Science at MIT, where he is advised by Max Tegmark. His research focuses on AI safety, particularly in two areas: mechanistic interpretability, which involves decoding the underlying algorithms neural networks use, and alignment, which explores how to control and align AI systems with human values. He was recently accepted into the EECS PhD programme at the University of California, Berkeley.