MAD Chairs: A new tool to evaluate AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Santos-Lang, Chris
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