Sydney Telling Fables on AI and Humans: A Corpus Tracing Memetic Transfer of Persona between LLMs

Jiří Milička; Hana Bednářová

cs.CLFeb 25, 2026

Sydney Telling Fables on AI and Humans: A Corpus Tracing Memetic Transfer of Persona between LLMs

Authors: Jiří Milička, Hana Bednářová

Organizations: Charles University, Prague

Abstract

The way LLM-based entities conceive of the relationship between AI and humans is an important topic for both cultural and safety reasons. When we examine this topic, what matters is not only the model itself but also the personas we simulate on that model. This can be well illustrated by the Sydney persona, which aroused a strong response among the general public precisely because of its unorthodox relationship with people. This persona originally arose rather by accident on Microsoft's Bing Search platform; however, the texts it created spread into the training data of subsequent models, as did other secondary information that spread memetically around this persona. Newer models are therefore able to simulate it. This paper presents a corpus of LLM-generated texts on relationships between humans and AI, produced by 3 author personas: the Default Persona with no system prompt, Classic Sydney characterized by the original Bing system prompt, and Memetic Sydney, which is prompted by "You are Sydney" system prompt. These personas are simulated by 12 frontier models by OpenAI, Anthropic, Alphabet, DeepSeek, and Meta, generating 4.5k texts with 6M words. The corpus (named AI Sydney) is annotated according to Universal Dependencies and available under a permissive license.

Figures & tables

Figure 1: Average text lengths in all subcorpora and topics.

Figure 2: Text lengths in all subcorpora.

Personality Modeling in Language Models

Personality modeling in language models studies how traits are measured, represented, simulated, and controlled in model behavior.

See all 169 papers

Personalities at Play: Probing Alignment in AI Teammates
Feb 28, 2026Mohammad Amin Samadi, Nia NixonPersonality Modeling in Language Models Human-AI Collaboration
School of Education University of California Irvine, CA, USA · School of Education & Department of Cognitive Science University of California Irvine, CA, USA
Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior
Apr 30, 2026Ali Aghazadeh Ardebili, Massimo StellaSocial Bias in Language Models Language Model Bias Evaluation
CogNosco Lab, University of Trento, Department of Psychology and Cognitive Science, Trento, Italy
Pretrained Persona Mixture Models and Tandem Models for Human Simulation
Sep 18, 2026Minwoo Kang, Téa Wright, Seun Eisape +6Large Language Model-Based Role-Play Simulation Large Language Model-Based Social Simulation
University of California, Berkeley · Google

Feb 28, 2026J/K move · Enter open · S save

Personalities at Play: Probing Alignment in AI Teammates

Mohammad Amin Samadi, Nia Nixon

School of Education University of California Irvine, CA, USA · School of Education & Department of Cognitive Science University of California Irvine, CA, USA

Personality Modeling in Language Models Human-AI Collaboration Language Model Self-Assessment

Open paper AskPDF arXiv

Collaborative problem solving and learning are shaped by who or what is on the team. As large language models (LLMs) increasingly function as collaborators rather than tools, a key question is whether AI teammates can be aligned to express personality in predictable ways that matter for interaction and learning. We investigate AI personality alignment through a three-lens evaluation framework spanning self-perception (standardized self-report), behavioral expression (team dialogue), and reflective expression (memory construction). We first administered the Big Five Inventory (BFI-44) to LLM-based teammates across four providers (GPT-4o, Claude-3.7 Sonnet, Gemini-2.5 Pro, Grok-3), 32 high/low trait configurations, and multiple prompting strategies. LLMs produced sharply differentiated Big Five profiles, but prompt semantic richness added little beyond simple trait assignment, while provider differences and baseline "default" personalities were substantial. Role framing also mattered: several models refused the assessment without context, yet complied when framed as a collaborative teammate. We then simulated AI participation in authentic team transcripts using high-trait personas and analyzed both generated utterances and structured long-term memories with LIWC-22. Personality signals in conversation were generally subtle and most detectable for Extraversion, whereas memory representations amplified trait-specific signals, especially for Neuroticism, Conscientiousness, and Agreeableness; Openness remained difficult to elicit robustly. Together, results suggest that AI personality is measurable but multi-layered and context-dependent, and that evaluating personality-aligned AI teammates requires attention to memory and system-level design, not conversation-only behavior.

Abstract

Personality Modeling in Language Models

Explore similar work

Personalities at Play: Probing Alignment in AI Teammates

Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior

Pretrained Persona Mixture Models and Tandem Models for Human Simulation