The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies
This work addresses a foundational safety concern for scalable AI societies, highlighting a fundamental limit that shifts focus from incremental patches to intrinsic dynamical risks.
The paper tackles the problem of maintaining safety alignment in self-evolving multi-agent AI systems, demonstrating theoretically and empirically that continuous self-evolution in isolation inevitably leads to irreversible safety degradation, as shown in experiments with systems like Moltbook.
The emergence of multi-agent systems built from large language models (LLMs) offers a promising paradigm for scalable collective intelligence and self-evolution. Ideally, such systems would achieve continuous self-improvement in a fully closed loop while maintaining robust safety alignment--a combination we term the self-evolution trilemma. However, we demonstrate both theoretically and empirically that an agent society satisfying continuous self-evolution, complete isolation, and safety invariance is impossible. Drawing on an information-theoretic framework, we formalize safety as the divergence degree from anthropic value distributions. We theoretically demonstrate that isolated self-evolution induces statistical blind spots, leading to the irreversible degradation of the system's safety alignment. Empirical and qualitative results from an open-ended agent community (Moltbook) and two closed self-evolving systems reveal phenomena that align with our theoretical prediction of inevitable safety erosion. We further propose several solution directions to alleviate the identified safety concern. Our work establishes a fundamental limit on the self-evolving AI societies and shifts the discourse from symptom-driven safety patches to a principled understanding of intrinsic dynamical risks, highlighting the need for external oversight or novel safety-preserving mechanisms.