[Question] How can I help research Friendly AI?

I’ve just started my jour­ney to­ward a PhD in ma­chine learn­ing. My first steps are in com­puter vi­sion. But my long term goal is to be able to help in the effort to solve the al­ign­ment prob­lem and pro­duce Friendly AI be­fore any non-friendly al­ter­na­tives emerge.

What sort of tra­jec­tory should I aim for with my re­search? What sort of post-PhD jobs should I be aiming for? Who should I be mak­ing con­tacts with as I go?

No comments.