We consider the dynamics of artificial chemistry systems consisting of small, interacting neural-network particles. Although recent explorations into properties of such systems have shown interesting phenomena, like self-replication tendencies, social interplay, and the ability for multi-objective applications, most of these settings are reasoned about in the abstract weight space. We extend this setup to involve an applied, stateful positioning task with mutual dependencies and show that stable configurations can be found jointly in both the weight space and 3D space. We show that the main contributing factor is enabling the networks to self-adapt their interaction rates depending on their internal stability or their ability to position themselves correctly. We find that this method effectively prepares the network assembly against potentially destabilizing interactions, promoting emergent stability while preventing convergence to trivial states.

We consider various setups where large language models (LLMs) communicate solely with themselves or other LLMs. In accordance with similar results known for program representations (like λ-expressions or automata), we observe a natural tendency for the evolution of self-replicating text pieces, i.e., LLM prompts that cause any receiving LLM to produce a response similar to the original prompt. We argue that the study of these self-replicating patterns, which exist in natural language and across different types of LLMs, may have important implications on artificial intelligence, cultural studies, and related fields.