Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.10779 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910947416735744 |
|---|---|
| author | Thomas, Philip S. |
| author_facet | Thomas, Philip S. |
| contents | This report explores the speculative question: what if current or future AI systems have qualia, such as pain or pleasure? It does so by assuming that AI systems might someday possess qualia -- and that the quality of these subjective experiences should be considered alongside performance metrics. Concrete mathematical problem settings, inspired by reinforcement learning formulations and theories from philosophy of mind, are then proposed and initial approaches and properties are presented. These properties enable refinement of the problem setting, culminating with the proposal of methods that promote reinforcement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10779 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Qualia Optimization Thomas, Philip S. Artificial Intelligence This report explores the speculative question: what if current or future AI systems have qualia, such as pain or pleasure? It does so by assuming that AI systems might someday possess qualia -- and that the quality of these subjective experiences should be considered alongside performance metrics. Concrete mathematical problem settings, inspired by reinforcement learning formulations and theories from philosophy of mind, are then proposed and initial approaches and properties are presented. These properties enable refinement of the problem setting, culminating with the proposal of methods that promote reinforcement. |
| title | Qualia Optimization |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2505.10779 |