Victor Warlop - Junior Research Fellow

Upon completing his graduate studies at Stanford University, Victor joined the Stanford Center for International Security and Cooperation, where he was assigned to lead the Stanford Existential Risks Initiative (SERI). Initially focusing on biosecurity, climate change, nuclear security, and AI alignment with the SERI team, he became increasingly worried about internal optimization objectives of future superintelligent systems, assigning an increasing likelihood on the emergence of powerseeking behaviour within these systems. He later spent two years as an independent researcher in AI Alignment, attempting to understand and formalize the possible dynamics for the emergence of solid and coherent value systems within such future superintelligent agents. Believing that defense institutions hold fundamental wisdoms required for coherent value systems, Victor joined NAVI hoping to engage in ongoing conversations with veterans of various nations about topics such as sacrifice, trust, legacy, duty, and honor - which he believes are capital concepts for the development of human-centered superintelligent AI’s.