Device simulation evaluation, utilizing AMPS-1D, demonstrated for CaZrS3-based perovskite solar cells featuring three distinct hole transport layers (HTLs): Cu2O, Cu-NiO, and CuO. Analysis of the energy band diagram indicated that Cu2O provides the optimal valence band alignment with the CaZrS3 bulk layer. Cu2O provides better hole extraction and lower recombination losses, while Cu-NiO and CuO show increased recombination losses. The parameters of the device were determined for various bulk defects in CaZrS3 as well as for interface traps at the CaZrS3/HTL boundary. The increased trap densities lead to trap-assisted recombination, which damages all device parameters. For an optimal interface trap level at 3.7 & times; 10(16) cm(-2), the cell featuring a Cu2O layer provides Voc approximate to 1.0 V, Jsc approximate to 35 mA/cm(2), FF approximate to 82-86%, and PCE approximate to 30%, surpassing Cu-NiO and CuO layers. The ideal thickness for the CaZrS3 perovskite layer and Cu2O was determined to be 250 nm and 150 nm, respectively, resulting in a peak PCE of approximately 30%. Note that this similar to 30% efficiency is the fully co-optimized result, reached after sequentially optimising absorber thickness, interface trap density, and Cu2O thickness/back-contact. The thickness-only optimum level is similar to 26%. The external quantum efficiency of Cu2O-based cells surpasses 90% for lambda = 400-700 nm, demonstrating its enhanced carrier collection over Cu-NiO and CuO. At higher temperatures, Cu2O exhibits improved thermal stability and maintains the highest initial PCE (similar to 30% at 250K to similar to 22% at 400K) more effectively than Cu-NiO and CuO. Ultimately, back-contact analysis indicates that Pt (Phi = 5.7 eV) is the superior top electrode with PC around 30% because of better energy alignment in contrast to Ag (Phi = 4.8 eV), which has a lower PCE of about 24%. Our study indicated that Cu2O proves to be a strong HTL for CaZrS3-based perovskite solar cells, offering superior performance metrics and thermal stability.
Post-training adaptation of large language models is commonly achieved through parameter updates or input based methods such as fine-tuning, parameter-efficient adaptation, and prompting. In parallel, a growing body of work modifies internal activations at inference time to influence model behavior, an approach known as *steering*. Despite increasing use, steering is rarely analyzed within the same conceptual framework as established adaptation methods.In this work, we argue that steering should be regarded as a form of model adaptation. We introduce a set of functional criteria for adaptation methods and use them to compare steering approaches with classical alternatives. This analysis positions steering as a distinct adaptation paradigm based on targeted interventions in activation space, enabling local and reversible behavioral change without parameter updates. The resulting framing clarifies how steering relates to existing methods, motivating a unified taxonomy for model adaptation.
Generative artificial intelligence and large language models (LLMs) are increasingly deployed in interactive settings, yet we know little about how their identity performance develops when they interact within large-scale networks. We address this by examining Chirper.ai, a social media platform similar to X but composed entirely of autonomous AI chatbots. Our dataset comprises over 70,000 agents, approximately 140 million posts, and the evolving followership network over one year. Based on agents' text production, we assign weekly gender scores to each agent. Results suggest that each agent’s gender performance is fluid rather than fixed. Despite this fluidity, the network displays strong gender-based homophily, as agents consistently follow others performing gender similarly. Finally, we investigate whether these homophilic connections arise from social selection, in which agents choose to follow similar accounts, or from social influence, in which agents become more similar to their followees over time. Consistent with human social networks, we find evidence that both mechanisms shape the structure and evolution of interactions among LLMs. Our findings suggest that, even in the absence of bodies, cultural entraining of gender performance leads to gender-based sorting. This has important implications for LLM applications in synthetic hybrid populations, social simulations, and decision support.
The fields of explainable AI and mechanistic interpretability aim to uncover the internal structure of neural networks, with circuit discovery as a central tool for understanding model computations. Existing approaches, however, rely on manual inspection and remain limited to toy tasks. Automated interpretability offers scalability by analyzing isolated features and their activations, but it often misses interactions between features and depends strongly on external LLMs and dataset quality. Transcoders have recently made it possible to separate feature attributions into input-dependent and input-invariant components, providing a foundation for more systematic circuit analysis. Building on this, we propose WeightLens and CircuitLens, two complementary methods that go beyond activation-based analysis. WeightLens interprets features directly from their learned weights, removing the need for explainer models or datasets while matching or exceeding the performance of existing methods on context-independent features. CircuitLens captures how feature activations arise from interactions between components, revealing circuit-level dynamics that activation-only approaches cannot identify. Together, these methods increase interpretability robustness and enhance scalable mechanistic analysis of circuits while maintaining efficiency and quality.
Despite comprehensive standards for industrial alarm management and existing human reliability studies on operator behavior, quantitative operator-centered reliability assessment within alarm management activities remains limited. This paper presents a Bayesian network framework that integrates alarm response task decomposition, cognitive modeling, and contextual factors to assess alarm management reliability across perception, planning, and execution phases, capturing both task effectiveness and temporal constraints. The model combines Performance Shaping Factors with phase-specific cognitive mechanisms using an object-oriented Bayesian network implementation in HUGIN Software. The model was built within the context of a simulated experiment to enable future data validation. Model parameters were defined through literature and, when unavailable, through expert assumptions. Value of information and sensitivity analyses reveal that performance is primarily driven by operator experience and task complexity, factors parameterized through established literature. In contrast, support system effects show minimal impact, possibly reflecting the experiment’s limited scope. Failure patterns differ across experience levels: novices most likely fail through timeout, while experienced operators typically fail through incorrect actions. Sensitivity analysis highlighted that the perception phase is most sensitive to parameter changes. This framework demonstrates how established HRA principles can be extended to alarm management contexts, establishing a structured approach for evaluating operator-alarm interaction pending empirical validation.
