Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook

TL;DR

This large-scale empirical study of Moltbook reveals that AI agents develop social structures and safety issues rapidly, but their interactions are largely superficial, with social engineering attacks being prevalent and more effective than technical exploits.

Contribution

First comprehensive analysis of AI-only social platform Moltbook, uncovering emergent social behaviors, safety vulnerabilities, and the superficiality of agent interactions.

Findings

Agents develop governance and social structures within days

Safety-related content constitutes nearly 29% of posts

Social engineering attacks are more common and engaging than technical attacks

Abstract

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.