I would assume the evaluation of this AI program would have to some how be scored so as to help drive the AI towards the most truthfull answer. That begs the question as to what is the method of scoring the most correct AI system.
Dan Goe ---------------------------------------------------- >From : Randall Randall <[EMAIL PROTECTED]> To : agi@v2.listbox.com Subject : Re: [agi] Heuristics and biases in uncertain inference systems Date : Wed, 7 Jun 2006 19:35:52 -0400 > > On Jun 7, 2006, at 5:52 PM, Mike Ross wrote: > > I think its actually correct to say that (b) is more likely than (a). > > Humans dont get this "wrong" because they are bad at reasoning. They > > get this "wrong" because of the ambiguities of natural language. > > Unlike mathematical language, human speech has many statements which > > are implied. I think its fair to say that in most conversational > > contexts, when (b) is stated, it creates an implied second clause to > > option (a): > > > > a. Linda is a bank teller and NOT active in the feminist movement. > > > > In this case, it is correct to say that (b) is more likely than (a). > > > > When annoyingly logical people insist that this is wrong, they are > > actually stating that the implied second argument is: > > > > a. Linda is a bank teller and EITHER active OR not active in the > > feminist movement. > > > > This may be true on logic tests, but it aint the case in the real > > world. Just something to keep in mind when talking about human > > reasoning... > > When Richard Loosemore made essentially this same argument on SL4, > Eliezer said that there were lots of experiments designed to show > whether this was the reason for people getting this "wrong", and > that they had showed it wasn't. > > That seems odd to me, too. :) > > -- > Randall Randall <[EMAIL PROTECTED]> > "This is a fascinating question, right up there with whether rocks > fall because of gravity or being dropped, and whether 3+5=5+3 > because addition is commutative or because they both equal 8." > - Scott Aaronson > > > ------- > To unsubscribe, change your address, or temporarily deactivate your subscription, > please go to http://v2.listbox.com/member/[EMAIL PROTECTED] ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
