We regularly meet up for discussions and workshops. These meetings are open to the public and you can see an overview in the calendar at the bottom of this page.
Every Tuesday we meet up at Høyteknologisenteret for a discussion group we are hosting. In these discussion groups, we go through AI Safety concepts and problems. At the moment we are going through a course in mechanistic interpretability. Besides that, we are also discussing generally interesting topics in AI safety.