The Most Important Open Problems in AGI Safety

In the last few minutes, maybe we can just go over some of what you see as the most important open problems in AGI safety. Steve: I'm particularly excited about trying to get a better handle on how the genome puts social instincts into us. And learning algorithms involved but that it's far from obvious exactly what their ground truth is. But I don't have an answer. More more eyes on that problem would be great so yeah I'm happy for people to be reading, yach punks up in neuro science textbooks and stuff like that.