AI Safety and Solutions with Robert Miles

Why is YouTube such a great way to communicate research findings? Why is AI safety (or alignment) a problem? Why is it an important problem? Why is the creation of AGI (artificial general intelligence) existentially risky for us? Why is it so hard for us to specify what we want in utility functions? What are some of the proposed strategies (and their limitations) for controlling AGI? What is instrumental convergence? What is the unilateralist's curse?

You can find Robert on YouTube.