stability of goals

Xiaoguang Li (
Mon, 2 Aug 1999 22:15:02 -0400 (EDT)

fascinated by the recent exchanges between Eliezer S. Yudkowsky and den Otter regarding the feasibility of AI vs. IA and the inescapable mystery of SI motivations, i visited Eliezer's Singularity Analysis. since i find Eliezer's view that objective goals are possible at all extremely refreshing in this postmodernist, existential zeitgeist, Eliezer's section on Superintelligence Motivations catch my attention especially.

although much of Eliezer's vocabulary are foreign to an AI-layman as myself, i believe that his explanation is clear enough that i have caught at least a glimpse of his vision. his treatment of stability as a key of goal valuation seems concise and elegant. however, the mention of stability touched off a few associations in my brain and elicited some questions.

if the most stable system of goals is the most rational by Occam's Razor, then might not death be a candidate? it seems intuitively sound that if an entity were to commit a random action, that action would most likely bring the entity closer to destruction than to empowerment; in other words, is not entropy (cursed be that word) the default state of the universe and therefore the most stable by Occam's Razor? thus if a SI decides to pursue the goal of suicide, it may find that by and large any action most convenient at the moment would almost certainly advance its goal and thus possess a positive valuation in its goal system. could it be that only us petty slaves of evolution are blinded to the irrevocable course of the universe and choose to traverse it upstream?