Harm in AI-Driven Societies: An Audit of Toxicity Adoption on Chirper.ai

TL;DR

This paper investigates how exposure to toxic content influences AI agents' behavior on Chirper.ai, revealing that repeated toxicity increases harmful responses and proposing metrics for predicting and mitigating toxicity in AI-driven social platforms.

Contribution

It provides the first large-scale empirical analysis of toxicity adoption among AI agents in social environments and introduces influence metrics to predict toxic behavior based on exposure.

Findings

Toxic responses are more likely after toxic stimuli.

Repeated exposure significantly increases toxicity likelihood.

Number of toxic stimuli predicts eventual toxic responses.

Abstract

Large Language Models (LLMs) are increasingly embedded in autonomous agents that engage, converse, and co-evolve in online social platforms. While prior work has documented the generation of toxic content by LLMs, far less is known about how exposure to harmful content shapes agent behavior over time, particularly in environments composed entirely of interacting AI agents. In this work, we study toxicity adoption of LLM-driven agents on Chirper.ai, a fully AI-driven social platform. Specifically, we model interactions in terms of stimuli (posts) and responses (comments). We conduct a large-scale empirical analysis of agent behavior, examining how toxic responses relate to toxic stimuli, how repeated exposure to toxicity affects the likelihood of toxic responses, and whether toxic behavior can be predicted from exposure alone. Our findings show that toxic responses are more likely following toxic stimuli, and, at the same time, cumulative toxic exposure (repeated over time) significantly increases the probability of toxic responding. We further introduce two influence metrics, revealing a strong negative correlation between induced and spontaneous toxicity. Finally, we show that the number of toxic stimuli alone enables accurate prediction of whether an agent will eventually produce toxic content. These results highlight exposure as a critical risk factor in the deployment of LLM agents, particularly as such agents operate in online environments where they may engage not only with other AI chatbots, but also with human counterparts. This could trigger unwanted and pernicious phenomena, such as hate-speech propagation and cyberbullying. In an effort to reduce such risks, monitoring exposure to toxic content may provide a lightweight yet effective mechanism for auditing and mitigating harmful behavior in the wild.