Vladimir_Nesov comments on Extraterrestrial paperclip maximizers - Less Wrong

3 Post author: multifoliaterose 08 August 2010 08:35PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (157)

You are viewing a single comment's thread. Show more comments above.

Comment author: Vladimir_Nesov 09 August 2010 10:06:49AM *  2 points [-]

Again, I would imagine that a battle between two AGIs would be determined by the amount of resources controlled within the proximate area of the battle.

Since they can trade globally, what's locally available must be irrelevant.

(I was talking about what it takes to stop a non-AGI civilization, hence a bit of misunderstanding.)

And if you get an alien AGI, you don't need to rush towards it, you only need to have had an opportunity to do so. Everyone is better off if instead of inefficiently running towards fighting the new AGI, you go about your business as usual, and later at your convenience the new AGI surrenders, delivering you all the control you could gain by focusing on fighting it and a bit more. Everyone wins.

Comment author: FAWS 09 August 2010 10:33:27AM *  1 point [-]

How do the AGI's model each other accurately enough to be able to acausally trade with each other like that? Is just using UDT/TDT enough? Probably. Is every sufficiently intelligent AGI going to switch to that, regardless of the decision theory it started out with, the way a CDT AGI would? Maybe there are possible alien decision theories that don't converge that way but are still winning enough to be a plausible threat?