When it comes to this issue, it makes more sense to think of another topic, frogs. Frogs eat insects all the time. This leads to a moral dilemma that will help us answer our question. Do the lives of insects matter more than the hunger of a frog? Situation 1...
This post is a response to Reward is not the optimization target, which someone recommended I read after I made a post on my blog. People have grown skeptical of the claim that an artificial intelligence would learn to intrinsically value reward over what the reward is tied to. I...
When it comes to this issue, it makes more sense to think of another topic, frogs. Frogs eat insects all the time. This leads to a moral dilemma that will help us answer our question. Do the lives of insects matter more than the hunger of a frog?
This is the answer most people would give, so I'm going to look at the implications first. We should allow frogs to continue eating insects, because their existence is more important than the insects'. If you are willing to accept this position, then you necessarily must allow the idea of higher and lower beings into your moral system. There is no way... (read 570 more words →)
This post is a response to Reward is not the optimization target, which someone recommended I read after I made a post on my blog.
People have grown skeptical of the claim that an artificial intelligence would learn to intrinsically value reward over what the reward is tied to. I would have to disagree. I am going to argue that any AI that would surpass its designers would have to value reward over it's goals, otherwise it wouldn't be smarter than its designers.
Being smarter than its designers is defined as coming up with solutions that the designers couldn't.
I am going to make a comparison of computers to humans and evolution. I will be... (read 1222 more words →)