I'm an indepedent AI existential safety researcher researching the promise of automating AI alignment and the intersection of deep learning, neuroscience and AI alignment. For more details, please see https://docs.google.com/document/d/1PchZ6o4sgSJBWFqGPCSHTbJNgr_el8VFsS55kJlENak/edit?usp=drive_link
