HackerPapers

arXiv:1707.08476cs.AI

Guidelines for Artificial Intelligence Containment

James Babcock, Janos Kramar, Roman V. Yampolskiy

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

With almost daily improvements in capabilities of artificial intelligence it is more important than ever to develop safety software for use by the AI research community. Building on our previous work on AI Containment Problem we propose a number of guidelines which should help AI safety researchers to develop reliable sandboxing software for intelligent programs of all levels. Such safety container software will make it possible to study and analyze intelligent artificial agent while maintaining certain level of safety against information leakage, social engineering attacks and cyberattacks from within the container.

arXiv comments
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence cs.CRCryptography and Security

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Oct 2024 to Oct 2024.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. Machines of loving grace: How AI could transform the world for the better 1 comment

    • Of course I grant the above point that software systems are not "ethereal". They have a physical form: often as electromagnetic states in matter. I hope my contribution to the conversation was clear: the nature of the physical embodiment matters. Things that are easy and cheap…

      xpeView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.