Self-Replicating Prompts for Large Language Models: Towards Artificial Culture
Gerhard Stenzel, Maximilian Zorn, Philipp Altmann, Maximilian Balthasar Mansky, Michael Kölle and Thomas Gabor
Abstract: 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.
Cite This Work
Switch between citation styles and copy the format you need.
Citation
Gerhard Stenzel, Maximilian Zorn, Philipp Altmann, Maximilian Balthasar Mansky, Michael Kölle, and Thomas Gabor. “Self-Replicating Prompts for Large Language Models: Towards Artificial Culture.” ALIFE 2024: Proceedings of the 2024 Artificial Life Conference , p. 110 , 2024. https://doi.org/10.1162/isal_a_00813