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.
翻译:传统安全工程正在进入一个转折点,从在明确情况下运行的决定性、非演变的系统转向在基本无法预测的操作环境中运行的日益自主和学习驱动的AI系统。 我们概述了安全AI的一些潜在挑战,并建议建立一个严格的工程框架,以尽量减少不确定性,从而提高对AI系统安全行为的信心,达到可容忍的程度。