A growing number of researchers are becoming concerned about the influence that AI agents could have on our future. In this discussion group, we’ll start by looking at whether those concerns are valid. Those who find the case for AI Safety to be compelling will spend the next 6 weeks learning about existing AI Safety technical research, efforts to implement policy measures that reduce AI risk, ways they can personally contribute to AI Safety, and more. The time commitment is 2 - 2.5 hours per week (1-1.5 1 hours of readings and 1 hour discussion). Check out our syllabus.