Military AI as a Convergent Goal of Self-Improving AI

by avturchin1 min read13th Nov 20173 comments


Instrumental ConvergenceAI Risk

This is our accepted chapter in the edited volume Forthcoming as a chapter in Artificial Safety And Security (Roman V. Yampolskiy , ed.), CRC Press.

>Abstract Better instruments to predict the future evolution of artificial intelligence (AI) are needed, as the destiny of our civilization depends on it. One of the ways to such prediction is the analysis of the convergent drives of any future AI, started by Omohundro. We show that one of the convergent drives of AI is a militarization drive, arising from AI’s need to wage a war against its potential rivals by either physical or software means, or to increase its bargaining power. This militarization trend increases global catastrophic risk or even existential risk during AI takeoff, which includes the use of nuclear weapons against rival AIs, blackmail by the threat of creating a global catastrophe, and the consequences of a war between two AIs. As a result, even benevolent AI may evolve into potentially dangerous military AI. The type and intensity of militarization drive depend on the relative speed of the AI takeoff and the number of potential rivals. We show that AI militarization drive and evolution of national defense will merge, as a superintelligence created in the defense environment will have quicker takeoff speeds, but a distorted value system. We conclude with peaceful alternatives. asa ConvergentGoal ofSelf-Improving AI

Link without registration and opened for commenting:

3 comments, sorted by Highlighting new comments since Today at 5:34 AM
New Comment

I assume you intended to add this link.

Yes, I thought that it will be link-post, but it looks like the link disaapeared from from the title? Maybe after I moved the post in the front page?

The UI is kind of confusing, but you can make a post either a link post or a text post but not both.