Mark waser writes: > P.S. You missed the time where Eliezer said at Ben's > AGI conference that he would sneak out the door before > warning others that the room was on fire :-) You people making public progress toward AGI are very brave indeed! I wonder if a time will come when the personal security of AGI researchers or conferences will be a real concern. Stopping AGI could be a high priority for existential-risk wingnuts. On a slightly related note, I notice that many (most?) AGI approaches do not include facilities for "recursive self-improvement" in the sense of giving the AGI access to its base source code and algorithms. I wonder if that approach is inherently safer, as the path to explosive self-improvement becomes much more difficult and unlikely to happen without being noticed. Personally I think that there is little danger that a properly-programmed GameBoy is going to suddenly recursively self-improve itself into a singularity-causing AGI, and the odds of any computer in the next 10 years at least being able to do so are only slightly higher.
----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415&user_secret=e9e40a7e
