Friendly artificial intelligence: Difference between revisions

Revision as of 15:41, 15 January 2024

Revision as of 17:18, 6 February 2024

Line 43:

In his book ''[[Human Compatible]]'', AI researcher [[Stuart J. Russell]] lists three principles to guide the development of beneficial machines. He emphasizes that these principles are not meant to be explicitly coded into the machines; rather, they are intended for the human developers. The principles are as follows:<ref name="HC">{{cite book |last=Russell |first=Stuart |date=October 8, 2019 |title=Human Compatible: Artificial Intelligence and the Problem of Control |url=https://archive.org/details/humancompatiblea0000russ |___location=United States |publisher=Viking |isbn=978-0-525-55861-3 |author-link=Stuart J. Russell |oclc=1083694322 |url-access=registration }}</ref>{{rp|173}}

{{quote|

{{quote|1.# The machine's only objective is to maximize the realization of human preferences.

2. #The machine is initially uncertain about what those preferences are.

3. #The ultimate source of information about human preferences is human behavior.}}

3. The ultimate source of information about human preferences is human behavior.}}

The "preferences" Russell refers to "are all-encompassing; they cover everything you might care about, arbitrarily far into the future."<ref name="HC"/>{{rp|173}} Similarly, "behavior" includes any choice between options,<ref name="HC"/>{{rp|177}} and the uncertainty is such that some probability, which may be quite small, must be assigned to every logically possible human preference.<ref name="HC"/>{{rp|201}}