Judd Rosenblatt is the CEO of AE Studio, a firm that shifted focus from brain-computer interfaces to AI alignment research, while Mike Vaiana serves as R&D Director, pioneering innovative approaches. They delve into biologically inspired methods for AI safety, emphasizing a unique self-other overlap for minimizing deception. Their research also addresses self-modeling in AI systems, highlighting the balance of predictability and cooperation. This thought-provoking dialogue showcases groundbreaking strategies that could reshape AI alignment and mitigate safety risks.