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.)
The most simple, able to self-improve "seed" for a superintelligence must be how complex?
Give your (wild) estimation or a pure guess in the terms of bits.
Do you reckon it is 1000 bits enough? At least 1000000 is required? More than 10^20 bits?
I wonder what your approximate numbers are.
Thank you!