I am working on a project about estimating alien density, their expected utility, and arguing for strategic implications. I am optimistic about the project producing valuable content to inform the AI safety strategy. But I want to probe what the community thinks beforehand.
Main question:
Assumptions:
Alien and Earth space-faring civilizations produce similar expected utilities [1]. The utility is computed using our CEV.
Alien space-faring civilizations are frequent enough such that there are at least several of them per affectable light cone such that very few resources are left unused.
Question:
Given the assumptions, what would the strategic implications be for the AI safety community?
Secondary question:
Without any assumption. What are your arguments for expecting Alien space-faring civilizations to have similar, or lower (e.g. 0), or higher expected utility than a future Earth-originating space-faring civilization?
Note: Please reach out to me by MP if you want to contribute or provide feedback on the project.
I am talking about the expected utility per unit of controlled resources, after considering everything. This is the “final” expected utility created per unit of resource. As an illustration, it accounts for the impact of trades and conflicts, causal or acausal, happening in the far future.
[Question] What are the strategic implications if aliens and Earth civilizations produce similar utilities?
I am working on a project about estimating alien density, their expected utility, and arguing for strategic implications. I am optimistic about the project producing valuable content to inform the AI safety strategy. But I want to probe what the community thinks beforehand.
Main question:
Assumptions:
Alien and Earth space-faring civilizations produce similar expected utilities [1]. The utility is computed using our CEV.
Alien space-faring civilizations are frequent enough such that there are at least several of them per affectable light cone such that very few resources are left unused.
Question:
Given the assumptions, what would the strategic implications be for the AI safety community?
Secondary question:
Without any assumption. What are your arguments for expecting Alien space-faring civilizations to have similar, or lower (e.g. 0), or higher expected utility than a future Earth-originating space-faring civilization?
Note: Please reach out to me by MP if you want to contribute or provide feedback on the project.
I am talking about the expected utility per unit of controlled resources, after considering everything. This is the “final” expected utility created per unit of resource. As an illustration, it accounts for the impact of trades and conflicts, causal or acausal, happening in the far future.