Still, even if an AGI is capable of simultaneously exploring in all directions, it may be inclined to send a disproportionately large amount of its resources (e.g. spaceships) in the direction of Earth with a view toward annihilating intelligent life on the Earth. After all, by the time it arrives at Earth, humans may have constructed their own AGI, so the factor determining whether the hypothetical extraterrestrial AGI can take over Earth may be the amount of resources that it sends toward the human civilization.
Also, maybe an AGI informed of our existence could utilize advanced technologies which we don’t know about yet to destroy us from afar (e.g. a cosmic ray generator?) and would not be inclined to utilize such technologies if it did not know of our existence (because using such hypothetical technologies could have side effects like releasing destructive radiation that detract from the AGI’s mission).
Still, even if an AGI is capable of simultaneously exploring in all directions, it may be inclined to send a disproportionately large amount of its resources (e.g. spaceships) in the direction of Earth with a view toward annihilating intelligent life on the Earth.
WHAT? It only takes one tiny probe with nanotech (femtotech?) and the right programming. “Colonization” (optimization, really) wave feeds on resources it encounters, so you only need to initiate it with a little bit of resources, it takes care of itself in the future.
I don’t follow this remark. 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. It would seem that maximizing the resources present in a given area (with a view toward winning a potential AGI battle) would entail diverting resources from other areas of the galaxy.
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.
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?
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.
Your points are fair.
Still, even if an AGI is capable of simultaneously exploring in all directions, it may be inclined to send a disproportionately large amount of its resources (e.g. spaceships) in the direction of Earth with a view toward annihilating intelligent life on the Earth. After all, by the time it arrives at Earth, humans may have constructed their own AGI, so the factor determining whether the hypothetical extraterrestrial AGI can take over Earth may be the amount of resources that it sends toward the human civilization.
Also, maybe an AGI informed of our existence could utilize advanced technologies which we don’t know about yet to destroy us from afar (e.g. a cosmic ray generator?) and would not be inclined to utilize such technologies if it did not know of our existence (because using such hypothetical technologies could have side effects like releasing destructive radiation that detract from the AGI’s mission).
WHAT? It only takes one tiny probe with nanotech (femtotech?) and the right programming. “Colonization” (optimization, really) wave feeds on resources it encounters, so you only need to initiate it with a little bit of resources, it takes care of itself in the future.
I don’t follow this remark. 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. It would seem that maximizing the resources present in a given area (with a view toward winning a potential AGI battle) would entail diverting resources from other areas of the galaxy.
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.
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?
Since they can trade globally, what’s locally available must be irrelevant.