MAD Chairs: A new tool to evaluate AI
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912572468363264 |
|---|---|
| author | Santos-Lang, Chris |
| author_facet | Santos-Lang, Chris |
| contents | This paper contributes a new way to evaluate AI. Much as one might evaluate a machine in terms of its performance at chess, this approach involves evaluating a machine in terms of its performance at a game called "MAD Chairs". At the time of writing, evaluation with this game exposed opportunities to improve Claude, Gemini, ChatGPT, Qwen and DeepSeek. Furthermore, this paper sets a stage for future innovation in game theory and AI safety by providing an example of success with non-standard approaches to each: studying a game beyond the scope of previous game theoretic tools and mitigating a serious AI safety risk in a way that requires neither determination of values nor their enforcement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20986 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MAD Chairs: A new tool to evaluate AI Santos-Lang, Chris Computers and Society Theoretical Economics 91A22 K.4.1 This paper contributes a new way to evaluate AI. Much as one might evaluate a machine in terms of its performance at chess, this approach involves evaluating a machine in terms of its performance at a game called "MAD Chairs". At the time of writing, evaluation with this game exposed opportunities to improve Claude, Gemini, ChatGPT, Qwen and DeepSeek. Furthermore, this paper sets a stage for future innovation in game theory and AI safety by providing an example of success with non-standard approaches to each: studying a game beyond the scope of previous game theoretic tools and mitigating a serious AI safety risk in a way that requires neither determination of values nor their enforcement. |
| title | MAD Chairs: A new tool to evaluate AI |
| topic | Computers and Society Theoretical Economics 91A22 K.4.1 |
| url | https://arxiv.org/abs/2503.20986 |