I’ve finally been able to put words to some things I’ve been pondering for awhile, and a Google search on the most sensible terms (to me) for these things turned up nothing. Looking to see if there’s already a body of writing on these topics using different terms, and my ignorance of such would lead to me just re-inventing the wheel in my ponderings. If these are NOT discussed topics for some reason, I’ll post my thoughts because I think they could be critically important to the development of Friendly AI.
implicit utility function (‘survive’ is an implicit utility function because regardless of what your explicit utility function is, you can’t progress it if you’re dead)
conflicted utility function (a utility function that requires your death for optimal value is conflicted, as in the famous Pig That Wants to be Eaten)
dynamic utility function (a static utility function is a major effectiveness handicap, probably a fatal one on a long enough time scale)
meta utility function (a utility function that takes the existence of itself into account)
Hey, never posted here before. Although I’ve sort of circled around the site for years and years, and I guess now I’m going down the drain, so to speak.
Well anyway, I registered because I had a very interesting experience earlier this week and I thought it might be of some interest to the community here. I suffered some sort of psychological or medical event (still not sure what, although my leading theories are dissociative episode or stroke) that seemed to either suppress my emotions or perhaps just my awareness of them. What followed was a sort of, as I later looked back on it, ‘pathological rationality’. Which is to say, given the information I had, I seemed to make solid inferences about what was likely to be true, and yet in many ways the whole thing was maladaptive from a survival standpoint.
One of the interesting things is that the morning after the event, while I was still affected, I wrote down my thoughts in a text file to help me evaluate them. Since returning to ‘normal’, I’ve reread that file multiple times, and I’m pretty fascinated by it. I thought others might also be.
I’m not really sure how to gauge the interest level nor get the information to those who would be interested in it without annoying those who wouldn’t be, though. Suggestions?