Roman Yampolskiy

In this name that follows Eastern Slavic naming customs, the patronymic is Vladimirovich and the family name is Yampolskiy.
Roman Yampolskiy
Роман Ямпольский
Yampolskiy in 2023
Born
Roman Vladimirovich Yampolskiy

(1979-08-13) 13 August 1979 (age 45)
Latvian SSR, Soviet Union
NationalityLatvian
Alma materUniversity at Buffalo
Scientific career
FieldsComputer science
Institutions

Roman Vladimirovich Yampolskiy (Russian: Роман Владимирович Ямпольский; born 13 August 1979) is a Latvian computer scientist at the University of Louisville, mostly known for his work on AI safety and cybersecurity. He holds a PhD from the University at Buffalo (2008).[1] He is the founder and current director of Cyber Security Lab, in the department of Computer Engineering and Computer Science at the Speed School of Engineering of the University of Louisville.[2]

Yampolskiy is an author of some 100 publications,[3] including numerous books.[4]

AI safety

Yampolskiy has warned of the possibility of existential risk from advanced artificial intelligence, and has advocated research into "boxing" artificial intelligence.[5] More broadly, Yampolskiy and his collaborator, Michaël Trazzi, have proposed in 2018 to introduce "Achilles' heels" into potentially dangerous AI, for example by barring an AI from accessing and modifying its own source code.[6][7] Another proposal is to apply a "security mindset" to AI safety, itemizing potential outcomes in order to better evaluate proposed safety mechanisms.[8]

He has suggested that there is no evidence of a solution to the AI control problem and has proposed pausing AI development, arguing that "Imagining humans can control superintelligent AI is a little like imagining that an ant can control the outcome of an NFL football game being played around it".[9][10] He joined AI researchers such as Yoshua Bengio and Stuart Russell in signing "Pause Giant AI Experiments: An Open Letter".[11]

In an appearance on the Lex Fridman podcast in 2024, Yampolskiy predicted the chance that AI could lead to human extinction at "99.9% within the next hundred years".[12]

Yampolskiy has been a research advisor of the Machine Intelligence Research Institute, and an AI safety fellow of the Foresight Institute.[13]

Intellectology

In 2015, Yampolskiy launched intellectology, a new field of study founded to analyze the forms and limits of intelligence.[14][15][16] Yampolskiy considers AI to be a sub-field of this.[14] 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.[17]

AI-Completeness

Yampolskiy has worked on developing the theory of AI-completeness, suggesting the Turing Test as a defining example.[18]

Books

  • Feature Extraction Approaches for Optical Character Recognition. Briviba Scientific Press, 2007, ISBN 0-6151-5511-1
  • Computer Security: from Passwords to Behavioral Biometrics. New Academic Publishing, 2008, ISBN 0-6152-1818-0
  • Game Strategy: a Novel Behavioral Biometric. Independent University Press, 2009, ISBN 0-578-03685-1
  • Artificial Superintelligence: a Futuristic Approach. Chapman and Hall/CRC Press (Taylor & Francis Group), 2015, ISBN 978-1482234435
  • AI: Unexplainable, Unpredictable, Uncontrollable. Chapman & Hall/CRC Press, 2024, ISBN 978-1032576268

See also

References

  1. ^ "Dr. Roman V. Yampolskiy, Computer Science, Speed School, University of Louisville, KY". Cecs.louisville.edu. Retrieved 25 September 2012.
  2. ^ "Cyber-Security Lab". University of Louisville. Retrieved 25 September 2012.
  3. ^ "Roman V. Yampolskiy". Google Scholar. Retrieved 25 September 2012.
  4. ^ "roman yampolskiy". Amazon.com. Retrieved 25 September 2012.
  5. ^ Hsu, Jeremy (1 March 2012). "Control dangerous AI before it controls us, one expert says". NBC News. Retrieved 28 January 2016.
  6. ^ Baraniuk, Chris (23 August 2018). "Artificial stupidity could help save humanity from an AI takeover". New Scientist. Retrieved 12 April 2020.
  7. ^ Trazzi, Michaël; Yampolskiy, Roman V. (2018). "Building safer AGI by introducing artificial stupidity". Arxiv.
  8. ^ Baraniuk, Chris (23 May 2016). "Checklist of worst-case scenarios could help prepare for evil AI". New Scientist. Retrieved 12 April 2020.
  9. ^ "There is no evidence that AI can be controlled, expert says". The Independent. 12 February 2024. Retrieved 4 July 2024.
  10. ^ McMillan, Tim (28 February 2024). "AI Superintelligence Alert: Expert Warns of Uncontrollable Risks, Calling It a Potential 'An Existential Catastrophe'". The Debrief. Retrieved 4 July 2024.
  11. ^ "Pause Giant AI Experiments: An Open Letter". Future of Life Institute. Retrieved 4 July 2024.
  12. ^ Altchek, Ana. "Why this AI researcher thinks there's a 99.9% chance AI wipes us out". Business Insider. Retrieved 13 June 2024.
  13. ^ "Roman Yampolskiy". Future of Life Institute. Retrieved 3 July 2024.
  14. ^ a b Yampolskiy, Roman V. (2015). Artificial Superintelligence: a Futuristic Approach. Chapman and Hall/CRC Press (Taylor & Francis Group). ISBN 978-1482234435.
  15. ^ "Intellectology and Other Ideas: A Review of Artificial Superintelligence". Technically Sentient. 20 September 2015. Archived from the original on 7 August 2016. Retrieved 22 November 2016.{{cite web}}: CS1 maint: bot: original URL status unknown (link)
  16. ^ "Roman Yampolskiy on Artificial Superintelligence". Singularity Weblog. 7 September 2015. Retrieved 22 November 2016.
  17. ^ 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.
  18. ^ Roman V. Yampolskiy. Turing Test as a Defining Feature of AI-Completeness. In Artificial Intelligence, Evolutionary Computation and Metaheuristics (AIECM) --In the footsteps of Alan Turing. Xin-She Yang (Ed.). pp. 3–17. (Chapter 1). Springer, London. 2013. http://cecs.louisville.edu/ry/TuringTestasaDefiningFeature04270003.pdf Archived 2013-05-22 at the Wayback Machine
Wikimedia Commons has media related to Roman Yampolskiy.