Adam S. Lowet

I like using machine learning to understand brains and using neuroscience to understand machines.

Adam S. Lowet

Hi there! I'm a neuro-AI researcher based in the San Francisco Bay Area interested in mechanistic interpretability, reinforcement learning, systems neuroscience, and AI safety. I'm currently conducting technical research on AI alignment with the Anthropic Fellows Progam, with a focus on interpretability. As such, I am on leave leave from my academic postdoc at UC Berkeley in the lab of Michael Yartsev, where I was developing state-of-the-art ML models for predicting and decoding hippocampal activity and — crucially — using those models to reveal novel computations underlying spatial cognition in naturalistic contexts. Before that, I completed my Ph.D. in Neuroscience at Harvard, where I worked with Naoshige Uchida on the neural circuit basis of distributional RL. Feel free to reach out to me with any comments or requests for collaboration!

Recent Updates