Safety Engineering for Artificial General Intelligence.
Machine ethics and robot rights are quickly becoming hot topics in artificial intelligence and robotics communities. We will argue that attempts to attribute moral agency and assign rights to all intelligent machines are misguided, whether applied to infrahuman or superhuman AIs, as are proposals to...
| Publicado en: | Topoi: An International Review of Philosophy Vol. 32; no. 2; pp. 217 - 227 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Oct2013
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=90309799&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 90309799 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 01677411 NM2 jtl: Topoi: An International Review of Philosophy issn: 01677411 maglogo: N pubinfo: dt: Oct2013 vid: 32 iid: 2 pid: 237 pub: Springer Nature artinfo: ui: 90309799 10.1007/s11245-012-9128-9 ppf: 217 ppct: 10 formats: fmt: @attributes: type: P size: 213KB tig: atl: Safety Engineering for Artificial General Intelligence. aug: au: Yampolskiy, Roman Fox, Joshua affil: Department of Computer Engineering and Computer Science, University of Louisville, Louisville 40292 USA Singularity Institute for Artificial Intelligence, Palo Alto USA su: General factor (Psychology) Industrial safety Robotics Moral agent (Philosophy) Self-actualization (Psychology) Autodidacticism sug: subj: General factor (Psychology) Industrial safety Robotics Moral agent (Philosophy) Self-actualization (Psychology) Autodidacticism keyword: AI confinement AI safety Friendly artificial intelligence Intelligence explosion Machine ethics Robot rights ab: Machine ethics and robot rights are quickly becoming hot topics in artificial intelligence and robotics communities. We will argue that attempts to attribute moral agency and assign rights to all intelligent machines are misguided, whether applied to infrahuman or superhuman AIs, as are proposals to limit the negative effects of AIs by constraining their behavior. As an alternative, we propose a new science of safety engineering for intelligent artificial agents based on maximizing for what humans value. In particular, we challenge the scientific community to develop intelligent systems that have human-friendly values that they provably retain, even under recursive self-improvement. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Topoi: An International Review of Philosophy is a copyright of Springer, 2013. All Rights Reserved. item: Topoi: An International Review of Philosophy holder: Springer Nature dt: @attributes: year: 2013 holdings: @attributes: islocal: N |
|---|