This is too confused to follow as a human, and much too confused to program an AI with.
Also ambiguity aside, (2) is just bad. I'm having trouble imagining a concrete interpretation of "don't over-optimize" that doesn't reduce to "fail to improve things that should be improved". And while short-sightedness is a problem for humans who have trouble modelling the future, I don't think AIs have that problem, and there are some interesting failure modes (of the destroys-humanity variety) that arise when an AI takes too much of a long view.
First and third paragraphs are attacks at the group, and the second is a rhetorical question (in the right direction). Please stick to object level. If you feel that your views are misrepresented, don't take offense: we try to make a more precise sense of what you say than your words let on, and can err in interpretation. The progress is made by moving forward, correcting the errors and arriving at common understanding. The progress is halted by taking offense, which leads to discouraging of further conversation even without outright stopping it.
If you consider a single top-level goal, then disclaimers about subgoals are unnecessary. Instead of saying "Don't overly optimize any given subgoal (at the expense of the other subgoals)", just say "Optimize the top-level goal". This is simpler and tells you what to do, as opposed to what not to do, with the latter suffering from all the problems of nonapples.
Now that I've got it, this is clear, concise, and helpful. Thank you.
I also owe you (personally) an apology for previous behavior.
In the spirit of Asimov’s 3 Laws of Robotics
It is my contention that Yudkowsky’s CEV converges to the following 3 points:
I further contend that, if this CEV is translated to the 3 Goals above and implemented in a Yudkowskian Benevolent Goal Architecture (BGA), that the result would be a Friendly AI.
It should be noted that evolution and history say that cooperation and ethics are stable attractors while submitting to slavery (when you don’t have to) is not. This formulation expands Singer’s Circles of Morality as far as they’ll go and tries to eliminate irrational Us-Them distinctions based on anything other than optimizing goals for everyone — the same direction that humanity seems headed in and exactly where current SIAI proposals come up short.
Once again, cross-posted here on my blog (unlike my last article, I have no idea whether this will be karma'd out of existence or not ;-)