All of Brad Dunn's Comments + Replies

Also worth mentioning this concept "Value learning" is called out specifically in Nick Bostrom's book, Superintelligence, with the use of the envelope puzzle which goes a little something like this; "Suppose we write down a description of a set of values on a piece of paper. We fold that paper and put it in a sealed envelope. We then create an agent with human-level general Intelligence and give it the following final goal; Maximize the realisation of the values described in the envelope."