Current cases of AI misalignment and their implications for future risks
Synthese · 26.10.2023 · 202 (5)
DOI: 10.1007/s11229-023-04367-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Synthese, online erschienen am 26.10.2023. Verfasst von Leonard Dung. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Friedrich-Alexander-Universität Erlangen-Nürnberg.
Abstract (Originalsprache)
How can one build AI systems such that they pursue the goals their designers want them to pursue? This is the alignment problem . Numerous authors have raised concerns that, as research advances and systems become more powerful over time, misalignment might lead to catastrophic outcomes, perhaps even to the extinction or permanent disempowerment of humanity. In this paper, I analyze the severity of this risk based on current instances of misalignment. More specifically, I argue that contemporary large language models and game-playing agents are sometimes misaligned. These cases suggest that misalignment tends to have a variety of features: misalignment can be hard to detect, predict and remedy, it does not depend on a specific architecture or training paradigm, it tends to diminish a system’s usefulness and it is the default outcome of creating AI via machine learning. Subsequently, based on these features, I show that the risk of AI alignment magnifies with respect to more capable systems. Not only might more capable systems cause more harm when misaligned, aligning them should be expected to be more difficult than aligning current AI.
Förderung
- Friedrich-Alexander-Universität Erlangen-Nürnberg
Zitieren
APA
Dung, L. (2023). Current cases of AI misalignment and their implications for future risks. Synthese, 202(5). https://doi.org/10.1007/s11229-023-04367-0
Vancouver
Dung L. Current cases of AI misalignment and their implications for future risks. Synthese. 2023;202(5). doi:10.1007/s11229-023-04367-0
BibTeX
@article{Dung2023,
author = {Dung, Leonard},
title = {Current cases of AI misalignment and their implications for future risks},
journal = {Synthese},
year = {2023},
volume = {202},
number = {5},
doi = {10.1007/s11229-023-04367-0}
}
EUVIMED