Unpredictability of AI: On the Impossibility of Accurately Predicting All Actions of a Smarter Agent
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
The young field of AI Safety is still in the process of identifying its challenges and limitations. In this paper, we formally describe one such impossibility result, namely Unpredictability of AI. We prove that it is impossible to precisely and consistently predict what specific actions a smarter-than-human intelligent system will take to achieve its objectives, even if we know the terminal goals of the system. In conclusion, the impact of Unpredictability on AI Safety is discussed.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Recent HCI studies on LLM-based tool design have mainly focused on prompt engineering [6,16,46,55,94,98] and exploring the generative capabilities of LLMs [50,58,63,67,97].”
From ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models (2024) · cites this paper as [94]
Citations
Cites
Impossibility of distributed consensus with one faulty process
Fischer, M. J., Lynch, N. A., & Paterson, M. S. (1985) · Journal of the ACM · doi:10.1145/3149.214121 · Cited by 4,579
On the impossibility of informationally efficient markets
Stiglitz, J. E., & Grossman, S. J. (1980) · Columbia University · doi:10.7916/d8765r99 · Cited by 3,645
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018) · Science · doi:10.1126/science.aar6404 · Cited by 3,562
Rahwan, I., Cebrian, M., Obradovich, N., Bongard, J., Bonnefon, J.-F., Breazeal, C., Crandall, J. W., Christakis, N. A., Couzin, I. D., Jackson, M. O., et al. (2019) · Nature · doi:10.1038/s41586-019-1138-y · Cited by 1,364
Campbell, M., Hoane, A. J., & Hsu, F.-H. (2002) · Artificial Intelligence · doi:10.1016/s0004-3702(01)00129-1 · Cited by 1,226
Classes of recursively enumerable sets and their decision problems
Rice, H. G. (1953) · Transactions of the American Mathematical Society · doi:10.1090/s0002-9947-1953-0053041-6 · Cited by 869
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
Brundage, M., Avin, S., Clark, J., Toner, H., Eckersley, P., Garfinkel, B., Dafoe, A., Scharre, P., Zeitzoff, T., Filar, B., et al. (2018) · Apollo - University of Cambridge Repository · doi:10.17863/cam.22520 · Cited by 849
Self-citationThe impossibility of moral responsibility
Strawson, G. (1994) · Philosophical Studies · doi:10.1007/bf00989879 · Cited by 814
Aggregating Sets of Judgments: An Impossibility Result
List, C., & Pettit, P. (2002) · Economics and Philosophy · doi:10.1017/s0266267102001098 · Cited by 619
Some Impossibility Theorems in Econometrics With Applications to Structural and Dynamic Models
Dufour, J.-M. (1997) · Econometrica · doi:10.2307/2171740 · Cited by 556
Research works printed but not linked: 10
- Bathaee Y., 2018, Harvard J. Law Technol., 31, 889
- Baum S., 2017, Informatica, 41, 419
- Bazerman M. H., 1997, Sloan Manage. Rev., 38, 89
- Grossman S. J., 1980, Am. Econo. Rev., 70, 393
- Mokhtarian E., 2018, Vanderbilt J. Entertainment Techol. Law, 21, 145
- Ramamoorthy A., 2018, ITU J, 1, 1
- Schmidhuber J., 2009, J. SICE, 48
- Turchin A., 2018, AI Soc., 1
- Wolfram S., 2002, A New Kind of Science, 5
- Yampolskiy R. V., 2018, Reti, saperi, linguaggi 2(2), 287
Cited by
Psychological factors underlying attitudes toward AI tools
De Freitas, J., Agarwal, S., Schmitt, B., & Haslam, N. (2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01734-2 · Cited by 221
Artificial suffering: an argument for a global moratorium on synthetic phenomenology
Metzinger, T. (2021) · Journal of Artificial Intelligence and Consciousness · doi:10.1142/s270507852150003x · Cited by 182
Williamson, S. M., & Prybutok, V. (2024) · Information · doi:10.3390/info15060299 · Cited by 146
Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response
Monett, D., Lewis, C. W. P., Þórisson, K. R., Bach, J., Baldassarre, G., Granato, G., Berkeley, I. S. N., Chollet, F., Crosby, M., Shevlin, H., et al. (2020) · Journal of Artificial General Intelligence · doi:10.2478/jagi-2020-0003 · Cited by 130
Self-citationUnexplainability and Incomprehensibility of AI
Yampolskiy, R. V. (2020) · Journal of Artificial Intelligence and Consciousness · doi:10.1142/s2705078520500150 · Cited by 107
Self-citation
Metadata
- Authors
- Yampolskiy, R. V.
- Affiliations
- University of Louisville (US)
- Corresponding author
- Yampolskiy, Roman V.
- ORCID
- Yampolskiy, Roman V.
- Venue
- Journal of Artificial Intelligence and Consciousness
- Publisher
- World Scientific Pub Co Pte Ltd
- Published
- 2020-03
- Volume
- 07
- Issue
- 01
- Pages
- 109-118
- ISSN
- 2705-0785 (ISSN-L)
- 2705-0793
- OpenAlex
- W3021366120
- Cited by
- 42
- References
- 22
- Citations by year
- 2026: 3 · 2025: 9 · 2024: 5 · 2023: 12 · 2022: 6 · 2021: 5 · 2020: 2
- FWCI
- 8.60
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Artificial Intelligence and Consciousness (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
- Keywords
- impossibility results, AI safety, action prediction, formal proof, human-level intelligence
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Unpredictability of AI: On the Impossibility of Accurately Predicting All Actions of a Smarter Agent. https://app.cochat.ai/papers/10.1142/s2705078520500034
- The paper
- Yampolskiy, R. V. (2020). Unpredictability of AI: On the Impossibility of Accurately Predicting All Actions of a Smarter Agent. Journal of Artificial Intelligence and Consciousness. https://doi.org/10.1142/s2705078520500034
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.