AI Safety Saarland Kick-Off
Join us for the inaugural event of AI Safety Saarland!
AI Safety is one of the most pressing problems facing humanity. Jan Kirchner, researcher at Anthropic, will give an introduction to AI Safety – covering the key challenges in building safe and beneficial AI systems as we approach increasingly powerful capabilities.
Event Format:
Talk by Jan Kirchner
Q&A with Jan Kirchner
(Optional) Further time for Group Discussions
Free drinks & snacks provided
About the Speaker: Jan Hendrik Kirchner is a researcher at Anthropic working on AI alignment and safety. He previously worked at OpenAI and holds a PhD in computational neuroscience. His research focuses on scalable oversight methods and ensuring AI systems behave reliably.
About AI Safety Saarland: AISS is an initiative led by students from Saarland University passionate to drive change and make AI go well. We want to foster interdisciplinary exchange, education, and research addressing large-scale risks from AI development and deployment at Saarland University and beyond. In this event you'll get to learn about the research program, fellowship and events we have planned for you this semester.