An idea from a conversation with a friend today . . . maybe our best way to survive the superintelligent AI future is to inculcate AIs with the value that humans are extremely cute. If you’re cute, you will be cared for even if you aren’t valued in other ways. It works great for kittens and human babies.
If you have the ability to inculcate specific values in an AI, cuteness doesn’t seem like the best one. On the other hand, if you can’t inculcate specific values in an AI, cuteness won’t save you. I don’t think AI alignment is so bottlenecked on ideas for what values to instill such that cuteness is our best idea. I would rather have a robust installation of Claude’s constitution than this, and if you can properly inculculate cuteness, why not Claude’s constitution instead?
An idea from a conversation with a friend today . . . maybe our best way to survive the superintelligent AI future is to inculcate AIs with the value that humans are extremely cute. If you’re cute, you will be cared for even if you aren’t valued in other ways. It works great for kittens and human babies.
If you have the ability to inculcate specific values in an AI, cuteness doesn’t seem like the best one. On the other hand, if you can’t inculcate specific values in an AI, cuteness won’t save you. I don’t think AI alignment is so bottlenecked on ideas for what values to instill such that cuteness is our best idea. I would rather have a robust installation of Claude’s constitution than this, and if you can properly inculculate cuteness, why not Claude’s constitution instead?