Introduction to AI Alignment

As we delegate more and more societal responsibilities to Artificial Intelligence, we raise pressing ethical questions about what will happen if these systems aren¿t aligned with our values. Many people, including AI experts like Stuart Russell, believe that there is an urgent need to mitigate the risks associated with future advanced AI systems and to ensure that their contributions are beneficial to humanity and the world. This 8-week course explores these questions in small discussion-based environments led by student facilitators with targeted readings, weekly group discussions, and an optional project. We will start by exploring arguments for and against the importance of AI alignment work, especially in relation to reducing existential risk. Then, we will learn about existing AI safety technical research, efforts to implement policy measures that reduce AI risk, and how you can personally contribute to AI safety.Enrollment is by application only. Apply at https://bit.ly/3BbOEk9 by October 9, 2022 by 9 PM.