LESSWRONG
LW

All of Saghey Sajeevan's Comments + Replies

All AGI safety questions welcome (especially basic ones) [Sept 2022]
Saghey Sajeevan10

Why wouldnt something like optimize for your goals whilst ensuring that the risk of harming a human is below x percent?

Reply
2Lone Pine
How do we know that the AI has a correct and reasonable instrumentation of the risk of harming a human? What if the AI has an incorrect definition of human, or deliberately corrupts its definition of human?