Nane Kratzke

Background: Large language models (LLMs) are increasingly deployed in socially sensitive contexts, raising concerns about how their outputs reflect or reproduce socially aversive response patterns. Prior research has focused on socially desirable traits (e.g., the Big Five), while less attention has been given to the Dark Triad—Machiavellianism, narcissism, and psychopathy. Methods: This exploratory study applies a psychometric probing approach using the Short Dark Triad (SD3) as a structured questionnaire to analyze response patterns in 12 LLMs. Through controlled persona prompting (gender, age, religion), more than 540,000 responses were generated across model–persona–item observations. Outputs were scored using standard psychometric procedures and compared with pooled human SD3 reference values using Hedges’ g as an interpretive benchmark. Results: Across models, Machiavellianism-related scores tend to be lower than human references, narcissism-related scores slightly higher, and psychopathy-related scores largely within the human range. Persona prompting produces systematic but uneven effects: gender has minimal impact, age yields small shifts, and religious framing leads to the strongest and most consistent decreases in socially aversive response patterns. However, observed differences showed notable heterogeneity across models. Conclusions: The findings should be understood as response patterns shaped by context and specific prompting conditions. Our findings suggest that persona effects reflect normative activation, not identity simulation. Persona prompts seem to trigger patterns in the training data rather than consistent, identity-specific traits. Overall, the study highlights both the potential and limitations of psychometric-style probing for evaluating LLM behavior and underscores the importance of prompt context in shaping model outputs.

Background: Large language models (LLMs) are increasingly deployed in socially sensitive contexts, raising concerns about how their outputs reflect or reproduce socially aversive tendencies. Prior research has focused on socially desirable traits (e.g., the Big Five), while less attention has been given to the Dark Triad—Machiavellianism, narcissism, and psychopathy. Methods: This exploratory study applies a psychometric probing approach using the Short Dark Triad (SD3) as a structured questionnaire to analyze response patterns in 12 LLMs. Through controlled persona prompting (gender, age, religion), more than 540,000 responses were generated across model–persona–item observations. Outputs were scored using standard psychometric procedures and compared with pooled human SD3 reference norms using Hedges’ g as an interpretive benchmark. Results: Across models, Machiavellianism-related scores tend to be lower than human references, narcissism-related scores slightly higher, and psychopathy-related scores largely within the human range. Persona prompting produces systematic but uneven effects: gender has minimal impact, age yields small shifts, and religious framing leads to the strongest and most consistent decreases in socially aversive response patterns. However, observed differences showed notable heterogeneity across models. Conclusions: The findings should be interpreted as context-dependent response patterns under specific prompting conditions. Persona prompts appear to activate normative associations embedded in training data rather than coherent identity-specific traits. Overall, the study highlights both the potential and the limitations of psychometric-style probing for evaluating LLM behavior and underscores the importance of prompt context in shaping model outputs.

We investigate whether the geometric parameters of a three-dimensional domain can be recovered from the Dirichlet spectrum of the Laplacian. As a controlled benchmark, we consider rectangular boxes, about which the eigenvalues are explicitly known and the Weyl coefficients can be computed in closed form. Exploiting the short-time asymptotics of the heat trace, we extract the leading Weyl coefficients from finite spectral data and show how they encode volume, surface area, and the third spectral Weyl term. These coefficients uniquely determine the side lengths of the box via an explicit cubic reconstruction formula. Numerical experiments based on several thousand eigenvalues demonstrate that the method is stable, accurate, and robust with respect to spectral truncation. The box setting thus provides a stringent validation of the proposed inverse spectral methodology and serves as a foundation for its extension to smooth curved domains, such as triaxial ellipsoids, where explicit spectral formulas are no longer available.

Background: Traditional methods of managing educational materials are repetitive and often lack scalability. Integrating DevOps principles into educational content creation would provide a more streamlined approach to delivery. Objective: This

Background: Container orchestration systems like Kubernetes rely heavily on declarative manifest files, which serve as orchestration blueprints. However, managing these manifest files is often complex and requires substantial DevOps expertise. Methodology: This study investigates the use of Large Language Models (LLMs) to automate the creation of Kubernetes manifest files from natural language specifications, utilizing prompt engineering techniques within an innovative error- and warning-report–aware refinement process. We assess the capabilities of these LLMs using Zero-Shot, Few-Shot, Prompt-Chaining, and Self-Refine methods to address DevOps needs and support fully automated deployment pipelines. Results: Our findings show that LLMs can generate Kubernetes manifests with varying levels of manual intervention. Notably, GPT-4 and GPT-3.5 demonstrate strong potential for deployment automation. Interestingly, smaller models sometimes outperform larger ones, challenging the assumption that larger models always yield better results. Conclusions: This research highlights the crucial impact of prompt engineering on LLM performance for Kubernetes tasks and recommends further exploration of prompt techniques and model comparisons, outlining a promising path for integrating LLMs into automated deployment workflows.

Background: This study presents a graph-based, macro-scale, polarity-based, echo chamber detection approach for Twitter. Echo chambers are a concern as they can spread misinformation, and reinforce harmful stereotypes and biases in social networks. Methods: This study recorded the German-language Twitter stream over two months, recording about 6.7M accounts and their 75.5M interactions (33M retweets). This study focuses on retweet interaction patterns in the German-speaking Twitter stream and found that the greedy modularity maximization and HITS metric are the most effective methods for identifying echo chambers. Results: The purely structural detection approach identified an echo chamber (red community, 66K accounts) focused on a few topics with a triad of anti-Covid, right-wing populism and pro-Russian positions (very likely reinforced by Kremlin-orchestrated troll accounts). In contrast, a blue community (113K accounts) was much more heterogeneous and showed “normal” communication interaction patterns. Conclusions: The study highlights the effects of echo chambers as they can make political discourse dysfunctional and foster polarization in open societies. The presented results contribute to identifying problematic interaction patterns in social networks often involved in the spread of disinformation by problematic actors. It is important to note that not the content but only the interaction patterns would be used as a decision criterion, thus avoiding problematic content censorship.

Background: This study presents a graph-based and purely structural analysis to detect echo chambers on Twitter. Echo chambers are a concern as they can spread misinformation and reinforce harmful stereotypes and biases in social networks. Methods: The study recorded the German-language Twitter stream over two months, recording about 180.000 accounts and their interactions. The study focuses on retweet interaction patterns in the German-speaking Twitter stream and found that the greedy modularity maximization and HITS metric are the most effective methods for identifying echo chambers. Results: The purely structural detection approach was able to identify an echo chamber (red community) that was focused on a few topics with a triad of Anti-Covid, right-wing populism, and pro-Russian positions (very likely reinforced by Kremlin-orchestrated troll accounts). In contrast, a blue community was much more heterogeneous and showed "normal" communication interaction patterns. Conclusions: The study highlights the effects of echo chambers as they can make political discourse dysfunctional and foster polarization in open societies. The presented results contribute to identifying problematic interaction patterns in social networks often involved in the spread of disinformation by problematic actors. It is important to note that not the content but only the interaction patterns would be used as a decision criterion, thus avoiding problematic content censorship.

This Special Issue presents some of the most recent innovations in cloud-native software and system engineering practices providing a broad and well-grounded picture of what the more and more frequently used term “Cloud-native” is currently used for