It seems like CEV style friendliness, for example, could at least be reduced to something on the order of complexity of a single “averaged” human brain.
That doesn’t sound like it passes the adequately-friendly-to-wedrifid test. I’d thermite such an AI rather than press the on button.
That seems difficult to determine without unpacking what I mean by “averaged”; how did you come to that conclusion? (I’m wondering if you have a clearer concept of what it would mean to “average” over brains, my intuition is nothing more than a sort of vague feeling that makes me think that I should study certain topics and ask certain questions) I don’t even know enough to accurately convey my intuition behind my use of “averaged”, I was just hoping that it might elicit a response from someone that would give me some useful information that would, in turn, help me in my task of understanding CEV better.
Unfortunately nobody has a good answer to your question. At least none that would satisfy me. The aggregation problem is the hardest part of the problem and hasn’t been answered adequately yet. Without such an answer CEV remains basically undefined. (This is something that troubles me.)
That doesn’t sound like it passes the adequately-friendly-to-wedrifid test. I’d thermite such an AI rather than press the on button.
That seems difficult to determine without unpacking what I mean by “averaged”; how did you come to that conclusion? (I’m wondering if you have a clearer concept of what it would mean to “average” over brains, my intuition is nothing more than a sort of vague feeling that makes me think that I should study certain topics and ask certain questions) I don’t even know enough to accurately convey my intuition behind my use of “averaged”, I was just hoping that it might elicit a response from someone that would give me some useful information that would, in turn, help me in my task of understanding CEV better.
Unfortunately nobody has a good answer to your question. At least none that would satisfy me. The aggregation problem is the hardest part of the problem and hasn’t been answered adequately yet. Without such an answer CEV remains basically undefined. (This is something that troubles me.)
I see. Thanks; that is enlightening. I had gotten the impression that this was the case, but wasn’t sure.