Basic AI drives
A basic AI drive is a goal or motivation that most intelligences will have or converge to. The idea was first explored by Stephen Omohundro. He argued that sufficiently advanced AI systems would all naturally discover similar instrumental subgoals. The concept was also explored by Nick Bostrom by the term instrumental convergence thesis. The main idea is that a few goals are instrumental to almost all possible final goals. Therefore, all AIs will pursue these instrumental goals. Omohundro uses microeconomic theory by von Neumann to support this idea.
In Bostrom's version, there are four main drives:
A sufficiently advanced AI will probably be the best entity to achieve its goals. Therefore, it must continue existing in order to maximize goal fulfillment. Similarly, if its goal system was modified, then it would likely begin pursuing different goals. Since this is not desirable to the current AI, it would act to preserve the content of its goal system.
At any time, the AI will have finite resources of time, space, matter, energy and computational power. Using these more efficiently will increase its utility. This will lead the AI to do things like implement more efficient algorithms, physical embodiments and precise mechanisms. It will also lead the AI to virtualize as much as possible.
Resources like matter and energy are fundamentally necessary to act. The more resources the AI can control, the more actions it can perform to achieve its goals. The AIs physical capabilities constitute its level of technology. For instance, if the AI could invent nanotechnology, it would vastly increase the actions it could take to achieve its goals.
The AIs operations will depend on its ability to come up with new, more efficient ideas. It will be driven to acquire more computational power for raw searching ability, and it will also be driven to search for better search algorithms. Omohundro argues that the drive for creativity is critical for the AI to display the richness and diversity that is valued by humanity. He discusses signaling goals as particularly rich sources of creativity.
In some rarer cases, AIs may not pursue these goals. For instance, if there are two AIs with the same goals, the less capable AI may determine that it should destroy itself to allow the stronger AI to control the universe. Or, an AI may have the goal of using as little resources as possible, or of being as unintelligent as possible. These goals will inherently limit the growth and power of the AI.
- Main article: Orthogonality thesis
Bostom also discusses a related thesis;
Intelligence and final goals are orthogonal axes along which possible agents can freely vary. In other words, more or less any level of intelligence could in principle be combined with more or less any final goal.
This thesis refers to final goals, while AI drives refer to instrumental goal, which would be used to achieve any final goals. Combining the theses, one could say that a sufficiently advanced AI may have almost any final goals, and will certainly pursue a few basic instrumental goals to gain these final goals.
- Orthogonality thesis
- Cox's theorem
- Unfriendly AI, Paperclip maximizer, Oracle AI
- Instrumental values
- Omohundro, S. (2007). The Nature of Self-Improving Artificial Intelligence. http://selfawaresystems.files.wordpress.com/2008/01/nature_of_self_improving_ai.pdf.
- Omohundro, S. (2008). "The Basic AI Drives". Proceedings of the First AGI Conference. http://selfawaresystems.com/2007/11/30/paper-on-the-basic-ai-drives/.
- Omohundro, S. (2012). Rational Artificial Intelligence for the Greater Good. http://selfawaresystems.files.wordpress.com/2012/03/rational_ai_greater_good.pdf.
- Bostrom, N. (2012). "The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents". Minds and Machines. http://www.nickbostrom.com/superintelligentwill.pdf.