Yampolskiy is an author of some 100 publications,[6] including numerous books.[7]
AI safety
Yampolskiy has warned of the possibility of
existential risk from advanced artificial intelligence, and has advocated research into "boxing" artificial intelligence.[8] More broadly, Yampolskiy and his collaborator, Michaël Trazzi, have proposed introducing "achilles heels" into potentially dangerous AI, for example by barring an AI from accessing and modifying its own source code.[9][10] Another proposal is to apply a "security mindset" to AI safety, itemizing potential outcomes in order to better evaluate proposed safety mechanisms.[11]
Intellectology
In 2015, Yampolskiy launched intellectology, a new field of study founded to analyze the forms and limits of intelligence.[12][13][14] Yampolskiy considers AI to be a sub-field of this.[12] An example of Yampolskiy's intellectology work is an attempt to determine the relation between various types of minds and the accessible
fun space, i.e. the space of non-boring activities.[15]
Books
Artificial Superintelligence: a Futuristic Approach. Chapman and Hall/CRC Press (Taylor & Francis Group), 2015,
ISBN978-1482234435.
Game Strategy: a Novel Behavioral Biometric. Independent University Press, 2009,
ISBN0-578-03685-1
Computer Security: from Passwords to Behavioral Biometrics. New Academic Publishing, 2008,
ISBN0-6152-1818-0
Feature Extraction Approaches for Optical Character Recognition. Briviba Scientific Press, 2007,
ISBN0-6151-5511-1
^
abYampolskiy, Roman V. (2015). Artificial Superintelligence: a Futuristic Approach. Chapman and Hall/CRC Press (Taylor & Francis Group).
ISBN978-1482234435.
^Ziesche, Soenke; Yampolskiy, Roman V. (2016). "Artificial Fun: Mapping Minds to the Space of Fun". 3rd Annual Global Online Conference on Information and Computer Technology (GOCICT16). Louisville, KY, USA. 16–18 November 2016.
arXiv:1606.07092.