Re: [agi] Friendly AI in an unfriendly world... AI to the future socieities.... Four axioms (WAS Two draft papers . . . .)

2006-06-12 Thread James Ratcliff
AIs only have the instincts and goals that they are built with. Theyare not, e.g., inherently territorial. They do not even inherently wantto survive. If you want them to have the goal of surviving, then youmust include that among their goals. You appear to be presuming that an FAI would have

[agi] Friendly AI in an unfriendly world... AI to the future socieities.... Four axioms (WAS Two draft papers . . . .)

2006-06-10 Thread DGoe
If your AI was operating on the web it might find itself at a sever disadvantage with all of those con artist... Your AI might lose bad... While being friendly might be nice. I think that is a vulnerable position to being taken advantage of... If you are in a war game-simulation or real

Re: [agi] Friendly AI in an unfriendly world... AI to the future socieities.... Four axioms (WAS Two draft papers . . . .)

2006-06-10 Thread Charles D Hixson
[EMAIL PROTECTED] wrote: If your AI was operating on the web it might find itself at a sever disadvantage with all of those con artist... Your AI might lose bad... Friendly does not equal trusting. It does not equal stupid. It does not equal not being willing to learn from the