Nope. I agree with the vast majority of the vetta definitions.
But let's go with Marcus Hutter - "There are strong arguments that AIXI is the most intelligent unbiased agent possible in the sense that AIXI behaves optimally in any computable environment."
Now, which is more optimal -- opting to play a positive-sum game of potentially infinite length and utility with cooperating humans OR passing up the game forever for a modest short-term gain?
Assume, for the purposes of argument, that the AGI does not have an immediate pressing need for the gain (since we could then go into a recursion of how pressing is the need -- and yes, if the need is pressing enough, the intelligent thing to do unless the agent's goal is to preserve humanity is to take the short-term gain and wipe out humanity -- but how would a super-intelligent AGI have gotten itself into that situation?). This should answer all of the questions about "Well, what if the AGI had a short-term preference and humans weren't it".
That definition doesn't explicity mention goals. Many of the definitions do explicity mention goals. What the definitions usually don't mention is what those goals are - and that permits super-villains, along the lines of General Zod.
If (as it appears) you want to argue that evolution is likely to produce super-saints - rather than super-villains - then that's a bit of a different topic. If you wanted to argue that, "requirement" was probably the wrong way of putting it.
[...] SIAI's Scary Idea goes way beyond the mere statement that there are risks as well as benefits associated with advanced AGI, and that AGI is a potential existential risk.
[...] Although an intense interest in rationalism is one of the hallmarks of the SIAI community, still I have not yet seen a clear logical argument for the Scary Idea laid out anywhere. (If I'm wrong, please send me the link, and I'll revise this post accordingly. Be aware that I've already at least skimmed everything Eliezer Yudkowsky has written on related topics.)
So if one wants a clear argument for the Scary Idea, one basically has to construct it oneself.
[...] If you put the above points all together, you come up with a heuristic argument for the Scary Idea. Roughly, the argument goes something like: If someone builds an advanced AGI without a provably Friendly architecture, probably it will have a hard takeoff, and then probably this will lead to a superhuman AGI system with an architecture drawn from the vast majority of mind-architectures that are not sufficiently harmonious with the complex, fragile human value system to make humans happy and keep humans around.
The line of argument makes sense, if you accept the premises.
But, I don't.
Ben Goertzel: The Singularity Institute's Scary Idea (and Why I Don't Buy It), October 29 2010. Thanks to XiXiDu for the pointer.