2000 character limit reached
Safe AI -- How is this Possible? (2201.10436v2)
Published 25 Jan 2022 in cs.AI
Abstract: Ttraditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems which are acting in largely unpredictable operating contexts. We outline some of underlying challenges of safe AI and suggest a rigorous engineering framework for minimizing uncertainty, thereby increasing confidence, up to tolerable levels, in the safe behavior of AI systems.