I pursue an interdisciplinary approach to AI alignment that synthesizes technical interpretability with human centric democratic principles. My technical focus centers on establishing robust superalignment by monitoring and governing the internal reasoning pathways of large language models rather than relying on superficial output regulation. Simultaneously, I advocate for a democratic alignment process where model behaviors are shaped by collective public voices rather than commercial entities. To guarantee that these systems truly serve human welfare, I integrate rigorous psychological measurement methodologies to continuously evaluate public cognitive and behavioral responses. Through this framework, I aim to bridge computational cognitive science and technical alignment to build secure and verifiable artificial general intelligence.
Sungkyunkwan University (SKKU)
Department of Psychology, Bachelor of Applied Artificial Intelligence, Feb 2025 - Exp. Feb 2028
University of Texas at Austin (Exchange Program)
Department of Psychology, Jan 2026 - May 2026
Gacheon University
Department of Psychology, Feb 2021 - Feb 2025
Human Language Intelligence Lab Internship
College of Computing and Informatics, Sungkyunkwan University (SKKU), June 2026 - Present
Developing Intelligence Lab Research Internship