Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.21664 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912399068495872 |
|---|---|
| author | O'Brien, Joe Dolan, Jeremy Kim, Jay Dykhuizen, Jonah Sania, Jeba Becker, Sebastian Kraprayoon, Jam Labrador, Cara |
| author_facet | O'Brien, Joe Dolan, Jeremy Kim, Jay Dykhuizen, Jonah Sania, Jeba Becker, Sebastian Kraprayoon, Jam Labrador, Cara |
| contents | Our survey of 53 specialists across 105 AI reliability and security research areas identifies the most promising research prospects to guide strategic AI R&D investment. As companies are seeking to develop AI systems with broadly human-level capabilities, research on reliability and security is urgently needed to ensure AI's benefits can be safely and broadly realized and prevent severe harms. This study is the first to quantify expert priorities across a comprehensive taxonomy of AI safety and security research directions and to produce a data-driven ranking of their potential impact. These rankings may support evidence-based decisions about how to effectively deploy resources toward AI reliability and security research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21664 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Expert Survey: AI Reliability & Security Research Priorities O'Brien, Joe Dolan, Jeremy Kim, Jay Dykhuizen, Jonah Sania, Jeba Becker, Sebastian Kraprayoon, Jam Labrador, Cara Computers and Society Artificial Intelligence Our survey of 53 specialists across 105 AI reliability and security research areas identifies the most promising research prospects to guide strategic AI R&D investment. As companies are seeking to develop AI systems with broadly human-level capabilities, research on reliability and security is urgently needed to ensure AI's benefits can be safely and broadly realized and prevent severe harms. This study is the first to quantify expert priorities across a comprehensive taxonomy of AI safety and security research directions and to produce a data-driven ranking of their potential impact. These rankings may support evidence-based decisions about how to effectively deploy resources toward AI reliability and security research. |
| title | Expert Survey: AI Reliability & Security Research Priorities |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2505.21664 |