RY
Roman Yampolskiy
cs.AIcs.CYcs.CRcs.OHcs.LGcs.NEbioinformaticsClassificationcs.CCcs.CV
On Valency
published · living versionsW_y3274kcu·v1 · currentpublished
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
with Miles Brundage, Shahar Avin, Jack Clark, Helen Toner +21
1 version
Preprints & journals
45 papers in the corpus · 2011–2025Unpredictability of AI1905.13053v1 · Roman V. Yampolskiy2019 · 8 citationsarXiv
The Right to Be Remembered: Preserving Maximally Truthful Digital Memory in the Age of AI2510.16206v2 · Alex Zhavoronkov, Dominika Wilczok, Roman Yampolskiy2025 · 0 citationsarXiv
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation1802.07228v2 · Miles Brundage, Shahar Avin, Jack Clark et al.2018 · 495 citationsarXivon Valency
Why We Do Not Evolve Software? Analysis of Evolutionary Algorithms.30546255 · Yampolskiy, Roman V2024 · 8 citationsEvolutionary bioinformatics online. 2018;14:1176934318815906
Understanding and Avoiding AI Failures: A Practical Guide2104.12582v4 · Heather M. Williams, Roman V. Yampolskiy2021 · 0 citationsarXiv
Impossibility Results in AI: A Survey2109.00484v2 · Mario Brcic, Roman V. Yampolskiy2021 · 23 citationsACM Computing Surveys, 2023
AI Risk Skepticism, A Comprehensive Survey2303.03885v1 · Vemir Michael Ambartsoumean, Roman V. Yampolskiy2023 · 6 citationsarXiv
Principles for new ASI Safety Paradigms2112.11184v2 · Erland Wittkotter, Roman Yampolskiy2021 · 0 citationsarXiv
Death in Genetic Algorithms2109.13744v1 · Micah Burkhardt, Roman V. Yampolskiy2021 · 0 citationsarXiv
AI Risk Skepticism2105.02704v3 · Roman V. Yampolskiy2021 · 1 citationarXiv
Transdisciplinary AI Observatory -- Retrospective Analyses and Future-Oriented Contradistinctions2012.02592v2 · Nadisha-Marie Aliman, Leon Kester, Roman Yampolskiy2020 · 3 citationsarXiv
Artificial Stupidity: Data We Need to Make Machines Our Equals.33205095 · Trazzi, Michaël, Yampolskiy, Roman V2020 · 11 citationsPatterns (New York, N.Y.). 2020;1(2):100021
Chess as a Testing Grounds for the Oracle Approach to AI Safety2010.02911v1 · James D. Miller, Roman Yampolskiy, Olle Haggstrom et al.2020 · 0 citationsarXiv
On Controllability of AI2008.04071v1 · Roman V. Yampolskiy2020 · 4 citationsarXiv
Human $\neq$ AGI2007.07710v1 · Roman V. Yampolskiy2020 · 2 citationsarXiv
The sounds of science: a symphony for many instruments and voices1907.05367v1 · Gerianne Alexander, Roland E. Allen, Anthony Atala et al.2019 · 15 citationsPhysica Scripta, v95 062501 (2020) [Available open access https://iopscience.iop.org/article/10.1088/1402-4896/ab7a35]
An AGI Modifying Its Utility Function in Violation of the Orthogonality Thesis2003.00812v1 · James D. Miller, Roman Yampolskiy, Olle Haggstrom2020 · 4 citationsarXiv
Classification Schemas for Artificial Intelligence Failures1907.07771v1 · Peter J. Scott, Roman V. Yampolskiy2019 · 26 citationsarXiv
Wisdom of artificial crowds feature selection in untargeted metabolomics: An application to the development of a blood-based diagnostic test for thrombotic myocardial infarction.29578100 · Trainor, Patrick J, Yampolskiy, Roman V, DeFilippis, Andrew P2019 · 16 citationsJournal of biomedical informatics. 2018;81:53-60
Unexplainability and Incomprehensibility of Artificial Intelligence1907.03869v1 · Roman V. Yampolskiy2019 · 9 citationsarXiv
An AGI with Time-Inconsistent Preferences1906.10536v1 · James D. Miller, Roman Yampolskiy2019 · 2 citationsarXiv
Simulation Typology and Termination Risks1905.05792v1 · Alexey Turchin, Michael Batin, David Denkenberger et al.2019 · 0 citationsarXiv
Personal Universes: A Solution to the Multi-Agent Value Alignment Problem1901.01851v1 · Roman V. Yampolskiy2019 · 12 citationsarXiv
Emergence of Addictive Behaviors in Reinforcement Learning Agents1811.05590v1 · Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir2018 · 4 citationsarXiv
Uploading Brain into Computer: Whom to Upload First?1811.03009v1 · Yana B. Feygin, Kelly Morris, Roman V. Yampolskiy2018 · 0 citationsarXiv
Optical Illusions Images Dataset1810.00415v2 · Robert Max Williams, Roman V. Yampolskiy2018 · 8 citationsarXiv
Why We Do Not Evolve Software? Analysis of Evolutionary Algorithms1810.07074v1 · Roman V. Yampolskiy2018 · 8 citationsarXiv
Human Indignity: From Legal AI Personhood to Selfish Memes1810.02724v1 · Roman V. Yampolskiy2018 · 0 citationsarXiv
Building Safer AGI by introducing Artificial Stupidity1808.03644v1 · Michael Trazzi, Roman V. Yampolskiy2018 · 15 citationsarXiv
A Psychopathological Approach to Safety Engineering in AI and AGI1805.08915v1 · Vahid Behzadan, Arslan Munir, Roman V. Yampolskiy2018 · 17 citationsarXiv
Detecting Qualia in Natural and Artificial Agents1712.04020v1 · Roman V. Yampolskiy2017 · 14 citationsarXiv
Towards Moral Autonomous Systems1703.04741v3 · Vicky Charisi, Louise Dennis, Michael Fisher et al.2017 · 47 citationsarXiv
Guidelines for Artificial Intelligence Containment1707.08476v1 · James Babcock, Janos Kramar, Roman V. Yampolskiy2017 · 31 citationsarXiv
Wisdom of artificial crowds feature selection in untargeted metabolomics: An application to the development of a blood-based diagnostic test for thrombotic myocardial infarction10.1101/165977v1 · Trainor, P. J., Yampolskiy, R. V., DeFilippis, A. P.2017 · 16 citationsbioRxiv
Evaluating race and sex diversity in the world's largest companies using deep neural networks1707.02353v1 · Konstantin Chekanov, Polina Mamoshina, Roman V. Yampolskiy et al.2017 · 4 citationsarXiv
Taxonomy of Pathways to Dangerous AI1511.03246v2 · Roman V. Yampolskiy2015 · 10 citationsin proceedings of 2nd International Workshop on AI, Ethics and Society (AIEthicsSociety2016). Pages 143-148. Phoenix, Arizona, USA. February 12-13th, 2016
Unethical Research: How to Create a Malevolent Artificial Intelligence1605.02817v2 · Federico Pistono, Roman V. Yampolskiy2016 · 40 citationsIn proceedings of Ethics for Artificial Intelligence Workshop (AI-Ethics-2016). Pages 1-7. New York, NY. July 9 -- 15, 2016
The Singularity May Be Near1706.01303v1 · Roman V. Yampolskiy2017 · 14 citationsarXiv
On the Origin of Samples: Attribution of Output to a Particular Algorithm1608.06172v1 · Roman V. Yampolskiy2016 · 16 citationsPhys. Scr. 92 (2017)
Verifier Theory and Unverifiability1609.00331v3 · Roman V. Yampolskiy2016 · 4 citationsarXiv
Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures1610.07997v1 · Roman V. Yampolskiy, M. S. Spellchecker2016 · 78 citationsarXiv
Artificial Fun: Mapping Minds to the Space of Fun1606.07092v1 · Soenke Ziesche, Roman V. Yampolskiy2016 · 1 citationarXiv
From Seed AI to Technological Singularity via Recursively Self-Improving Software1502.06512v1 · Roman V. Yampolskiy2015 · 10 citationsarXiv
The Universe of Minds1410.0369v1 · Roman V. Yampolskiy2014 · 6 citationsarXiv
Construction of an NP Problem with an Exponential Lower Bound1111.0305v1 · Roman V. Yampolskiy2011 · 9 citationsarXiv
Career total: 253 works. 45 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.