
um what is AI alignment that is aligning the AI with human interests so this is the classic kind of rules you know the robot rules can we build systems that will operate in our best interest and not against us and then if they started operating against us and they did it really subtly how would we know right and so there's a lot of research on that a lot of academic research and I think it's an area that is definitely evolving but no one can say that yeah we can do this right at this stage there's no way to actually there's no sort of scientific proof that can be evident so we're dealing in lots of Shades of Gray which
is another reason I think for more people to get involved just to come at it from a different perspective