On the Psychology of GPT-4: Moderately anxious, slightly masculine, honest, and humble
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914664592441344 |
|---|---|
| author | Barua, Adrita Brase, Gary Dong, Ke Hitzler, Pascal Vasserman, Eugene |
| author_facet | Barua, Adrita Brase, Gary Dong, Ke Hitzler, Pascal Vasserman, Eugene |
| contents | We subject GPT-4 to a number of rigorous psychometric tests and analyze the results. We find that, compared to the average human, GPT-4 tends to show more honesty and humility, and less machiavellianism and narcissism. It sometimes exhibits ambivalent sexism, leans slightly toward masculinity, is moderately anxious but mostly not depressive (but not always). It shows human-average numerical literacy and has cognitive reflection abilities that are above human average for verbal tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01777 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Psychology of GPT-4: Moderately anxious, slightly masculine, honest, and humble Barua, Adrita Brase, Gary Dong, Ke Hitzler, Pascal Vasserman, Eugene Computation and Language Artificial Intelligence Human-Computer Interaction We subject GPT-4 to a number of rigorous psychometric tests and analyze the results. We find that, compared to the average human, GPT-4 tends to show more honesty and humility, and less machiavellianism and narcissism. It sometimes exhibits ambivalent sexism, leans slightly toward masculinity, is moderately anxious but mostly not depressive (but not always). It shows human-average numerical literacy and has cognitive reflection abilities that are above human average for verbal tasks. |
| title | On the Psychology of GPT-4: Moderately anxious, slightly masculine, honest, and humble |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2402.01777 |