Artificial Intelligence: Approaches to Safety
Fuente:
Wiley Open Access
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Artículo Open Access |
| Veröffentlicht: |
Wiley
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1867006804456636416 |
|---|---|
| author | William D'Alessandro Cameron Domenico Kirk‐Giannini |
| author_facet | William D'Alessandro Cameron Domenico Kirk‐Giannini William D'Alessandro Cameron Domenico Kirk‐Giannini |
| collection | Wiley Open Access |
| contents | Artificial Intelligence: Approaches to Safety William D'Alessandro Cameron Domenico Kirk‐Giannini Philosophy Compass ABSTRACT AI safety is an interdisciplinary field focused on mitigating the harms caused by AI systems. We review a range of research directions in AI safety, focusing on those to which philosophers have made or are in a position to make the most significant contributions. These include ethical AI , which seeks to instill human goals, values, and ethical principles into artificial systems, scalable oversight , which seeks to develop methods for supervising the activity of artificial systems even when they become significantly more capable than their human designers, interpretability , which seeks to render comprehensible the workings of complex machine learning models, and corrigibility , which seeks to discover ways to ensure that powerful AI systems will not resist being shut down or modified by humans. 10.1111/phc3.70039 http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| doi_str_mv | 10.1111/phc3.70039 |
| format | Artículo Open Access |
| id | wiley_oa_10_1111_phc3_70039 |
| institution | Wiley Open Access |
| license_str_mv | http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| publishDate | 2025 |
| publisher | Wiley |
| record_format | wiley_oa |
| spellingShingle | Artificial Intelligence: Approaches to Safety William D'Alessandro Cameron Domenico Kirk‐Giannini Philosophy Compass Artificial Intelligence: Approaches to Safety William D'Alessandro Cameron Domenico Kirk‐Giannini Philosophy Compass ABSTRACT AI safety is an interdisciplinary field focused on mitigating the harms caused by AI systems. We review a range of research directions in AI safety, focusing on those to which philosophers have made or are in a position to make the most significant contributions. These include ethical AI , which seeks to instill human goals, values, and ethical principles into artificial systems, scalable oversight , which seeks to develop methods for supervising the activity of artificial systems even when they become significantly more capable than their human designers, interpretability , which seeks to render comprehensible the workings of complex machine learning models, and corrigibility , which seeks to discover ways to ensure that powerful AI systems will not resist being shut down or modified by humans. 10.1111/phc3.70039 http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| title | Artificial Intelligence: Approaches to Safety |
| topic | Philosophy Compass |
| url | https://compass.onlinelibrary.wiley.com/doi/10.1111/phc3.70039 |