Re: [agi] Motivational Systems that are stable

[Mark Waser]

>> Although I understand, in vague terms, what idea Richard is attempting to express, I don't see why having "massive numbers of weak constraints" or "large numbers of connections from [the] motivational system to [the] thinking system." gives any more reason to believe it is reliably Friendly (without any further specification of the actual processes) than one with "few numbers of strong constraints" or "a small number of connections between the motivational system and the thinking system".   Which is more likely to fail (or be subverted) a) a chain with single links b) a highly interconnected net/web   Which one do you want to "chain the beast" with? 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/[EMAIL PROTECTED]