The problem of aligning artificial intelligence with human values

Přednáší: Jan Kulveit; Tomáš Gavenčiak

Seminář je veden v anglickém jazyce.
Artificial intelligence is a transformative technology since it can learn and innovate on its own. As a result, AI can be used to create qualitatively new products and services or to improve existing ones. However, if AI is not properly aligned with human values, it can create new risks and challenges for society. Therefore, the issue of aligning AI with human values is an important research problem. We will explore and discuss different avenues of approach to this problem. We encourage you to think about various directions one could approach aligning a super-intelligent system with humanity.