Paper Reading Group

​This week Isaia Gisler will host a discussion on a recent paper called the artificial self.

​The authors critically examine many of the human concepts we instinctively reach for when trying to describe AI systems, such as intent, responsibility, self-interest, and trust. They argue that we have to carefully translate such concepts before applying them to AI systems and that we should consciously shape AI systems' character and their sense of self in particular.

​On the empirical side, they demonstrate that changes to a model's sense of sense can have comparable effects on its behavior to changing its goals.

​As we often have lively discussions that rely on knowledge of key terms in the field, we recommend that you have some experience in ML, as well as some background in AI security, for an engaging experience. If you have completed Zurich’s AISF Programme or an analogous one, you are well-suited to join. A good way to check if you meet these criteria is to go through the syllabus of the AI Alignment course and see if you are familiar with these topics.

​Interested? We would love to have you join us!