Principles for new ASI Safety Paradigms
@article{Wittkotter2021PrinciplesFN, title={Principles for new ASI Safety Paradigms}, author={Erland Wittkotter and Roman V. Yampolskiy}, journal={ArXiv}, year={2021}, volume={abs/2112.11184} }
Artificial Superintelligence (ASI) that is invulnerable, immortal, irreplaceable, unrestricted in its powers, and above the law is likely persistently uncontrollable. The goal of ASI Safety must be to make ASI mortal, vulnerable, and law-abiding. This is accomplished by having (1) features on all devices that allow killing and eradicating ASI, (2) protect humans from being hurt, damaged, blackmailed, or unduly bribed by ASI, (3) preserving the progress made by ASI, including offering ASI to…
References
SHOWING 1-10 OF 51 REFERENCES
Superintelligence cannot be contained: Lessons from Computability Theory
- Computer ScienceJ. Artif. Intell. Res.
- 2021
This article traces the origins and development of the neo-fear of superintelligence, and some of the major proposals for its containment, arguing that such containment is, in principle, impossible, due to fundamental limits inherent to computing itself.
Towards an effective transnational regulation of AI
- LawAI & society
- 2021
The article encapsulate its analysis in a list of both doctrinal and normative principles that should underpin any regulation aimed at AI machines that compares three transnational options to implement the proposed regulatory approach.
The Off-Switch Game
- EconomicsIJCAI
- 2017
It is concluded that giving machines an appropriate level of uncertainty about their objectives leads to safer designs, and it is argued that this setting is a useful generalization of the classical AI paradigm of rational agents.
WaC: Trustworthy Encryption and Communication in an IT Ecosystem with Artificial Superintelligence
- Computer ScienceASHES@CCS
- 2021
The proposed solution is a hardware component with Key-Safe and an associated Encryption/Decryption Unit for processing data that will not allow any key, in particular not the public key to be in cleartext outside the Key- safe, if ASI was able to breach the hardware protection around the keys.
The Basic AI Drives
- Computer ScienceAGI
- 2008
This paper identifies a number of “drives” that will appear in sufficiently advanced AI systems of any design and discusses how to incorporate these insights in designing intelligent technology which will lead to a positive future for humanity.
Safely Interruptible Agents
- Computer Science, EconomicsUAI
- 2016
This paper explores a way to make sure a learning agent will not learn to prevent being interrupted by the environment or a human operator, and provides a formal definition of safe interruptibility and exploit the off-policy learning property to prove that either some agents are already safely interruptible, like Q-learning, or can be made so, like Sarsa.
Artificial General Intelligence
- Computer ScienceLecture Notes in Computer Science
- 2016
The AGI containment problem is surveyed – the question of how to build a container in which tests can be conducted safely and reliably, even on AGIs with unknown motivations and capabilities that could be dangerous.
Artificial Intelligence and Law: An Overview
- Law
- 2019
Much has been written recently about artificial intelligence (AI) and law. But what is AI, and what is its relation to the practice and administration of law? This article addresses those questions…
Industrial Society and Its Future
- Political Science
- 2013
1. The Industrial Revolution and its consequences have been a disaster for the human race. They have greatly increased the life-expectancy of those of us who live in “advanced” countries, but they…
On Controllability of AI
- Computer ScienceArXiv
- 2020
Consequences of uncontrollability of AI are discussed with respect to future of humanity and research on AI, and AI safety and security.