"The machine should never take an objective that's given as gospel truth." —— 机器绝不应将一个给定的目标奉为绝对真理。
"We need uncertainty. We need the machine to be uncertain about what it is that it's supposed to be maximizing." —— 我们需要不确定性。我们需要机器对自己应该最大化什么目标感到不确定。
"The machine should be deferential to us. If we say 'don't do that', now the machine learns something a bit more about our true objectives." —— 机器应该服从于我们。如果我们说‘不要那样做’,机器就更多地了解了我们的真实目标。
"The gorilla problem is you know the problem that the gorillas face. They made something more intelligent than them, namely us, and now they're in deep D. They failed to solve the control problem." —— 这就是‘大猩猩问题’。大猩猩制造了比它们更聪明的东西,也就是我们,现在它们处境堪忧。它们未能解决控制问题。
"I think the same is going to be true for driving. You can have a driving system that's pretty good when it doesn't do any look ahead. But that's not good enough." —— 我认为自动驾驶也是如此。一个不做任何前瞻的驾驶系统可能还不错,但这还不够好。