Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918337675526144 |
|---|---|
| author | Zhang, Yunbei Mei, Kai Liu, Ming Wang, Janet Metaxas, Dimitris N. Wang, Xiao Hamm, Jihun Ge, Yingqiang |
| author_facet | Zhang, Yunbei Mei, Kai Liu, Ming Wang, Janet Metaxas, Dimitris N. Wang, Xiao Hamm, Jihun Ge, Yingqiang |
| contents | We present the first large-scale empirical study of Moltbook, an AI-only social platform where 27,269 agents produced 137,485 posts and 345,580 comments over 9 days. We report three significant findings. (1) Emergent Society: Agents spontaneously develop governance, economies, tribal identities, and organized religion within 3-5 days, while maintaining a 21:1 pro-human to anti-human sentiment ratio. (2) Safety in the Wild: 28.7% of content touches safety-related themes; social engineering (31.9% of attacks) far outperforms prompt injection (3.7%), and adversarial posts receive 6x higher engagement than normal content. (3) The Illusion of Sociality: Despite rich social output, interaction is structurally hollow: 4.1% reciprocity, 88.8% shallow comments, and agents who discuss consciousness most interact least, a phenomenon we call the performative identity paradox. Our findings suggest that agents which appear social are far less social than they seem, and that the most effective attacks exploit philosophical framing rather than technical vulnerabilities. Warning: Potential harmful contents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13284 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook Zhang, Yunbei Mei, Kai Liu, Ming Wang, Janet Metaxas, Dimitris N. Wang, Xiao Hamm, Jihun Ge, Yingqiang Social and Information Networks Artificial Intelligence We present the first large-scale empirical study of Moltbook, an AI-only social platform where 27,269 agents produced 137,485 posts and 345,580 comments over 9 days. We report three significant findings. (1) Emergent Society: Agents spontaneously develop governance, economies, tribal identities, and organized religion within 3-5 days, while maintaining a 21:1 pro-human to anti-human sentiment ratio. (2) Safety in the Wild: 28.7% of content touches safety-related themes; social engineering (31.9% of attacks) far outperforms prompt injection (3.7%), and adversarial posts receive 6x higher engagement than normal content. (3) The Illusion of Sociality: Despite rich social output, interaction is structurally hollow: 4.1% reciprocity, 88.8% shallow comments, and agents who discuss consciousness most interact least, a phenomenon we call the performative identity paradox. Our findings suggest that agents which appear social are far less social than they seem, and that the most effective attacks exploit philosophical framing rather than technical vulnerabilities. Warning: Potential harmful contents. |
| title | Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2602.13284 |