I'm Coby Kassner, and I'm an AI safety researcher with interest in control and science of generalization. I have a broader interest in most things related to macrostrategy , existential risk, analytical philosophy , and effective altruism / AI safety fieldbuilding. In my free time, I love composing and performing music, dancing Argentine tango, and mountaineering. I'm currently studying at Yale, where I help organize the effective altruism and AI alignment groups.