Impossibility Results in AI: A Survey
ACM Computing Surveys, Volume 56, Issue 1, 1–24
Abstract
This survey systematically catalogs impossibility results across AI research, organizing them by domain (deductive, inductive, intractability, unprovability, unfairness, ethical) and analyzing their implications for AI safety, alignment, and the design of trustworthy AI systems. We argue that understanding these formal limits is foundational to setting realistic expectations and identifying genuinely hard problems in the field.
Notes
Comprehensive survey of formal impossibility results across AI subdomains, with implications for AI safety and the limits of what AI systems can provably achieve. One of the foundational references for theoretical AI safety work.
How to cite
@article{brcic2023brcic,
author = {Mario Brcic and Roman V. Yampolskiy},
title = {Impossibility Results in AI: A Survey},
journal = {ACM Computing Surveys, Volume 56, Issue 1, 1–24},
year = {2023},
doi = {10.1145/3603371},
}Topics: