HCIstudio introduced students to Human-Computer Interaction and Virtual Reality during Girls’ Day 2026 in Adlershof.

HCIstudio participated in the ACM CHI Conference on Human Factors in Computing Systems, the leading international conference on Human-Computer Interaction.

HCIstudio organized the CHI 2026 workshop “The AI Accomplice” on generative AI and deceptive design.

Prompt engineering is often treated as a reliable control mechanism for LLM behavior, yet LLM outputs vary even under similar prompts due to stochasticity. We quantify how much output variance is driven by prompt choice versus model choice and by inherent within-LLM stochasticity by evaluating 12 LLMs on 10 creativity prompts in an open-ended divergent-thinking task (AUT), measuring answer quality (originality) and quantity (number of answers), generating 100 samples per prompt. Then, we partition the variance into model, prompt, within-LLM stochasticity, and model×prompt interaction components. Our findings show that model choice is at least as important as prompt choice in this setting. For originality, the model explains 41% of the variance. Prompts explain 36%, and within-model stochasticity explains 11%. For fluency, prompts explain 4% of the variance. Model choice explains 51%, and within-model stochasticity 34%. Beyond variance decomposition, models exhibit persistent “creative fingerprints” in thematic preferences and formatting habits. CHI

Large language models (LLMs) are increasingly employed in HumanComputer Interaction (HCI) research to simulate human behavior for prototype testing and social simulations. The validity of these interactions rests on the assumption that LLMs maintain stable personas. Our work investigates temporal stability in LLM-based human simulation, examining both stability across independent instantiations and within extended interactions. We combined selfreports with observer-ratings of four persona intensity levels (low, moderate, and high ADHD representations, default persona), seven LLMs, and three persona prompts. Results from 𝑁 = 3, 473 conversations and 𝑁 = 4, 054 assessments indicate that LLMs generally reproduce personas across conversations in self-reports and observer ratings, suggesting that LLMs hold promise as tools for simulating human behavior. Within extended 18-turn interactions, observer ratings reveal a decline for moderate and high personas, a discrepancy that warrants further investigation. Our findings indicate methodological considerations for HCI researchers employing LLM-based human simulation and implications for future research.

As generative Artificial Intelligence (AI) becomes increasingly embedded and utilized for digital design, it presents both opportunities and risks. One major concern is its potential to facilitate and incorporate deceptive design patterns into computing technologies, which could manipulate or mislead users to their disadvantage. Similar to the concept of precedent-based design, a common approach in design theory that suggests reapplying previous design solutions to similar or identical problems, generative AI can integrate deceptive design patterns included in the training data a model has seen before. Our workshop explores how generative AI suggests and enacts deceptive design patterns in digital design. The goal of the workshop is to explore the ethical challenges of utilizing generative AI models and develop strategies to detect or prevent manipulative practices, thereby creating more transparent and equitable AI-generated experiences.