Cargando…

An unethical optimization principle

If an artificial intelligence aims to maximize risk-adjusted return, then under mild conditions it is disproportionately likely to pick an unethical strategy unless the objective function allows sufficiently for this risk. Even if the proportion η of available unethical strategies is small, the prob...

Descripción completa

Detalles Bibliográficos
Autores principales: Beale, Nicholas, Battey, Heather, Davison, Anthony C., MacKay, Robert S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7428226/
https://www.ncbi.nlm.nih.gov/pubmed/32874640
http://dx.doi.org/10.1098/rsos.200462