Eliezer thinks he can write a self-modifying AI that will self-modify to want the same things its original self wanted. I’m proposing that he choose a different thing for the AI to want that will be easier to code, as an intermediate step to building a truly friendly AI.
I’ve read that.
Eliezer thinks he can write a self-modifying AI that will self-modify to want the same things its original self wanted. I’m proposing that he choose a different thing for the AI to want that will be easier to code, as an intermediate step to building a truly friendly AI.