Robert Schaefer just pointed me (via a mailing-list note) to a list of features of “AI safety”, via a reference in the blog of Victoria Krakovna at https://vkrakovna.wordpress.com/2018/11/01/discussion-on-the-machine-learning-approach-to-ai-safety/ . The features of “AI safety” pointed to, from  http://www.foldl.me/2018/conceptual-issues-ai-safety-paradigmatic-gap/ , are Short-term: This work involves immediately practical safety risks in deploying machine learning systems. These include data poisoning, training set…