Guardat en:
| Autor principal: | |
|---|---|
| Format: | Recurso digital |
| Idioma: | japonès |
| Publicat: |
Zenodo
2026
|
| Matèries: | |
| Accés en línia: | https://doi.org/10.5281/zenodo.19637287 |
| Etiquetes: |
Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
Taula de continguts:
- <p>Advances in artificial intelligence (AI) technology have led to progress in various fields, and further results are expected. However, the possibility of uncontrollable behavior, known as AI runaway, has also been pointed out.</p> <p>The possibility of AI becoming self-serving, deviating from human intentions, and taking undesirable actions, or posing dangers to society and humanity, is a significant issue. If AI runaway occurs, it could lead to serious accidents or threats to national security.</p> <p>The purpose of this research is to study what can be done to prevent AI runaway, improve AI safety, and prevent such runaway behavior, and to propose methods for achieving this.</p>