The AI off-switch problem as a signalling game: bounded rationality and incomparability
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909559165026304 |
|---|---|
| author | Benavoli, Alessio Facchini, Alessandro Zaffalon, Marco |
| author_facet | Benavoli, Alessio Facchini, Alessandro Zaffalon, Marco |
| contents | The off-switch problem is a critical challenge in AI control: if an AI system resists being switched off, it poses a significant risk. In this paper, we model the off-switch problem as a signalling game, where a human decision-maker communicates its preferences about some underlying decision problem to an AI agent, which then selects actions to maximise the human's utility. We assume that the human is a bounded rational agent and explore various bounded rationality mechanisms. Using real machine learning models, we reprove prior results and demonstrate that a necessary condition for an AI system to refrain from disabling its off-switch is its uncertainty about the human's utility. We also analyse how message costs influence optimal strategies and extend the analysis to scenarios involving incomparability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06403 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The AI off-switch problem as a signalling game: bounded rationality and incomparability Benavoli, Alessio Facchini, Alessandro Zaffalon, Marco Machine Learning The off-switch problem is a critical challenge in AI control: if an AI system resists being switched off, it poses a significant risk. In this paper, we model the off-switch problem as a signalling game, where a human decision-maker communicates its preferences about some underlying decision problem to an AI agent, which then selects actions to maximise the human's utility. We assume that the human is a bounded rational agent and explore various bounded rationality mechanisms. Using real machine learning models, we reprove prior results and demonstrate that a necessary condition for an AI system to refrain from disabling its off-switch is its uncertainty about the human's utility. We also analyse how message costs influence optimal strategies and extend the analysis to scenarios involving incomparability. |
| title | The AI off-switch problem as a signalling game: bounded rationality and incomparability |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.06403 |