> You are placing your aesthetic preferences for how an AGI "should"
> work over the data regarding how real intelligences do work.
> Knowledge clearly becomes proceduralized and inaccessible to reasoning
> with use.
I see your point now. I guess proceduralization is quite necessary for efficiency, rather than searching the state-space every time a problem arises. My professor told a story where he discovered a new route to commute to university which is more convenient, but for years he's been taking the longer route.
As Ben said, his AGI stores procedures in a different place from declarative knowledge, so it is compatible with my current model.
I'm only starting to think about the action/planning aspects of AGI. It seems that the AGI need to search for solutions when none exists (obviously), and sometimes to search for better solutions if the cost is too high, and other times just stick with the last solution in a similar context -- that answers Pei Wang's critique.
YKY
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
