EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

If We Succeed

Stuart Russell

Daedalus · 01.05.2022 · 151 (2) · 43-57

DOI: 10.1162/daed_a_01899 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Daedalus, online erschienen am 01.05.2022. Verfasst von Stuart Russell. Die Arbeit wurde bisher 12-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitieren

Abstract (Originalsprache)

Since its inception, AI has operated within a standard model whereby systems are designed to optimize a fixed, known objective. This model has been increasingly successful. I briefly summarize the state of the art and its likely evolution over the next decade. Substantial breakthroughs leading to general-purpose AI are much harder to predict, but they will have an enormous impact on society. At the same time, the standard model will become progressively untenable in real-world applications because of the difficulty of specifying objectives completely and correctly. I propose a new model for AI development in which the machine's uncertainty about the true objective leads to qualitatively new modes of behavior that are more robust, controllable, and deferential.

Zitieren

APA

Russell, S. (2022). If We Succeed. Daedalus, 151(2), 43-57. https://doi.org/10.1162/daed_a_01899

Vancouver

Russell S. If We Succeed. Daedalus. 2022;151(2):43-57. doi:10.1162/daed_a_01899

BibTeX
@article{Russell2022,
  author = {Russell, Stuart},
  title = {If We Succeed},
  journal = {Daedalus},
  year = {2022},
  volume = {151},
  number = {2},
  pages = {43--57},
  doi = {10.1162/daed_a_01899}
}
Kostenlos starten →