Thinking Inside the Box: Controlling and Using an Oracle AI

Abstract There is no strong reason to believe that human-level intelligence represents an upper limit of the capacity of artificial intelligence, should it be realized. This poses serious safety issues, since a superintelligent system would have great power to direct the future according to its poss...
Ausführliche Beschreibung

Gespeichert in:
Autor*in:

Armstrong, Stuart [verfasserIn]

Sandberg, Anders [verfasserIn]

Bostrom, Nick [verfasserIn]

Format:

E-Artikel

Sprache:

Englisch

Erschienen:

2012

Schlagwörter:

Artificial intelligence

Superintelligence

Security

Risks

Motivational control

Capability control

Übergeordnetes Werk:

Enthalten in: Minds and machines - Dordrecht [u.a.] : Springer Science + Business Media B.V, 1991, 22(2012), 4 vom: 06. Juni, Seite 299-324

Übergeordnetes Werk:

volume:22 ; year:2012 ; number:4 ; day:06 ; month:06 ; pages:299-324

Links:

Volltext

DOI / URN:

10.1007/s11023-012-9282-2

Katalog-ID:

SPR015802914

Nicht das Richtige dabei?

Schreiben Sie uns!