The Elephant in the Room -- Why AI Safety Demands Diverse Teams
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913430466723840 |
|---|---|
| author | Rostcheck, David Scheibling, Lara |
| author_facet | Rostcheck, David Scheibling, Lara |
| contents | We consider that existing approaches to AI "safety" and "alignment" may not be using the most effective tools, teams, or approaches. We suggest that an alternative and better approach to the problem may be to treat alignment as a social science problem, since the social sciences enjoy a rich toolkit of models for understanding and aligning motivation and behavior, much of which could be repurposed to problems involving AI models, and enumerate reasons why this is so. We introduce an alternate alignment approach informed by social science tools and characterized by three steps: 1. defining a positive desired social outcome for human/AI collaboration as the goal or "North Star," 2. properly framing knowns and unknowns, and 3. forming diverse teams to investigate, observe, and navigate emerging challenges in alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10254 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Elephant in the Room -- Why AI Safety Demands Diverse Teams Rostcheck, David Scheibling, Lara Computers and Society Artificial Intelligence We consider that existing approaches to AI "safety" and "alignment" may not be using the most effective tools, teams, or approaches. We suggest that an alternative and better approach to the problem may be to treat alignment as a social science problem, since the social sciences enjoy a rich toolkit of models for understanding and aligning motivation and behavior, much of which could be repurposed to problems involving AI models, and enumerate reasons why this is so. We introduce an alternate alignment approach informed by social science tools and characterized by three steps: 1. defining a positive desired social outcome for human/AI collaboration as the goal or "North Star," 2. properly framing knowns and unknowns, and 3. forming diverse teams to investigate, observe, and navigate emerging challenges in alignment. |
| title | The Elephant in the Room -- Why AI Safety Demands Diverse Teams |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2407.10254 |