paperclip maximizer
English edit
Alternative forms edit
Etymology edit
Described by Swedish philosopher Nick Bostrom in 2003.[1]
Noun edit
paperclip maximizer (plural paperclip maximizers)
- A hypothetical artificial intelligence whose goal is to produce as many paperclips as possible and which achieves this by converting all matter in the universe into paperclips.
- 2016 October 3, Tad Friend, “Sam Altman’s Manifest Destiny”, in The New Yorker[2]:
- The problem of managing powerful systems that lack human values is exemplified by “the paperclip maximizer,” a scenario that the Swedish philosopher Nick Bostrom raised in 2003.
- 2016, Olle Häggström, Here Be Dragons: Science, Technology and the Future of Humanity, Oxford University Press, page 116:
- An instructive and oft-repeated example introduced by Bostrom (2003c) is the paperclip maximizer. The seed AI is given the goal of producing as many paperclips as it can.
- 2017, Amir Husain, The Sentient Machine: The Coming Age of Artifical Intelligence, Souvenir Press:
- A psychopathic leader in control of a sophisticated ANI system portends a far greater risk in the near term than a paperclip maximizer.
- 2019, Ben Orlin, Change Is the Only Constant: The Wisdom of Calculus in a Madcap World, New York: Black Dog & Leventhal Publishers, page 137:
- If the Paperclip Maximizer destroys the world for a silly goal, why don’t you and I destroy the world, given our goals can be less than benign?
References edit
- ^ Nick Bostrom (2003) “Ethical Issues in Advanced Artificial Intelligence”, in I. Smit et al., editors, Cognitive, Emotive and Ethical Aspects of Decision Making in Humans and in Artificial Intelligence[1], volume 2, Int. Institute of Advanced Studies in Systems Research and Cybernetics, pages 12–17
Further reading edit
Instrumental convergence § Paperclip maximizer on Wikipedia.Wikipedia
