Joe Kwon is a Technical Advisor for AI Capability Assessment for the Recursive Self Improvement Initiative at the Institute for Security and Technology. Joe is a technical AI safety and governance researcher whose work centers around safe frontier AI development practices and forecasting AI risks. Previously, he worked on threat modeling with Forethought, AI governance with GovAI, multilingual LLMs at LG AI Research, and empirical ML safety + computational cognitive science at MIT. Joe graduated with a bachelors in computer science and psychology from Yale University.