Large language models (LLMs) excel in providing natural language responses that sound authoritative, reflect knowledge of the context area, and can present from a range of varied perspectives. Agent Based Models and Simulation consist of simulated agents that interact within a simulated environment to explore societal, social, and ethical, among other, problems. Agents generate large volumes of data over time and discerning useful and relevant content is an onerous task. LLMs can help in communicating agents’ perspectives on key events by providing natural language narratives. However, these narratives need to be factual, transparent, and reproducible. To this end, we present a structured narrative prompt for sending queries to LLMs. Chi-square tests and Fisher’s Exact tests are applied to assess statistically significant difference in sentiment scores of the narrative messages between simulation generated narratives, ChatGPT-generated narratives, and real tweets. The narrative prompt structure effectively yields narratives with the desired components from ChatGPT. This structure is expected to be extensible across LLMs. In 14 out of 44 categories, ChatGPT generated narratives which has sentiment scores that were not discernibly different, in terms of statistical significance (alpha level of 0.05), from the sentiment expressed in real tweets. Three outcomes are provided: (1) a list of benefits and challenges for LLMs in narrative generation; (2) a structured prompt for requesting narratives of a LLM based on simulated agents’ information; and (3) an assessment of statistical significance in the sentiment prevalence of the generated narratives compared to real tweets. This indicates significant promise in the utilization of LLMs for helping to connect simulated agent’s experiences with real people.

This primer provides an overview of the rapidly evolving field of generative artificial intelligence, specifically focusing on large language models like ChatGPT (OpenAI) and Bard (Google). Large language models have demonstrated unprecedented capabilities in responding to natural language prompts. The aim of this primer is to demystify the underlying theory and architecture of large language models, providing intuitive explanations for a broader audience. Learners seeking to gain insight into the technical underpinnings of large language models must sift through rapidly growing and fragmented literature on the topic. This primer brings all the main concepts into a single digestible document. Topics covered include text tokenization, vocabulary construction, token embedding, context embedding with attention mechanisms, artificial neural networks, and objective functions in model training. The primer also explores state-of-the-art methods in training large language models to generalize on specific applications and to align with human intentions. Finally, an introduction to the concept of prompt engineering highlights the importance of effective human-machine interaction through natural language in harnessing the full potential of artificial intelligence chatbots. This comprehensive yet accessible primer will benefit students and researchers seeking foundational knowledge and a deeper understanding of the inner workings of existing and emerging artificial intelligence models. The author hopes that the primer will encourage further responsible innovation and informed discussions about these increasingly powerful tools.

Diet-related diseases impact populations across the globe. While intertemporal preferences—a fundamental preference for the distribution of benefits across time—have been used to explain low-quality food choices, recent literature proposes another cause: inattention to future implications (or opportunity costs) of the options faced. Food choices tend to become habitual to conserve cognitive resources, rather than carefully modeling future health impacts. Both low discount rates for future benefits and attention to future health impacts predict healthier decisions. While intertemporal preferences are stable, attention may provide an opportunity to intervene in the decision process to promote healthier decisions. In this study, we test the impact of a simple message that highlights health during food choice on the healthiness of foods chosen and on health consideration and intertemporal preferences. Our results show that actively considering health outcomes and lower discount rates lead to healthier food choices. We find that messaging increases the consideration of health outcomes during food choice but does not affect intertemporal preferences, suggesting that simple prompts may be an effective way to promote decisions balancing short and long-term benefits by drawing attention to overlooked opportunity costs of choices.

This study investigates the impact of geomagnetic storms that occurred on June 8, 22-23, and 25, 2015, on the ionosphere in the low-latitude and equatorial regions of Brazil. By examining various data sources, such as solar wind parameters from the ACE satellite, GPS vertical total electron content (VTEC), magnetometer data, and the SAMI2 model, we aimed to simulate the effects of storms on the ionosphere in these regions. Two methods were employed to separate DP2 and Disturbance dynamo (Ddyn) from the ionospheric disturbance current (Diono). Our analysis revealed a positive (negative) ionospheric storm in the VTEC during the main phase (recovery) of the June 22-23 and 25 storms. This observation can be attributed to the combined impact of the eastward prompt penetration of the magnetospheric convection electric field (westward disturbance dynamo electric field) and changes in the storm-time thermospheric [O]/[N_2] ratio based on the GUVI satellite imagery. Notably, the westward disturbance dynamo exhibited a significant amplitude on June 23 in Belem. The amplitude of the D_dyn at Belem (dip lat: - 0.47˚) was greater than that at Alta Floresta (dip lat: - 3.75˚) due to intensified cowling conductivity in Belem. Furthermore, we found that the SAMI2 model provided more accurate results when we replaced the default ExB drift with the vertical drift calculated from the ground-based magnetometer, enabling us to simulate the effect of the westward DDEF on VTEC during daytime.

This research investigates the potential application of generative language models, especially ChatGPT, in aviation safety analysis as a means to enhance the efficiency of safety analyses and accelerate the time it takes to process incident reports. In particular, ChatGPT was leveraged to generate incident synopses from narratives, which were subsequently compared with ground truth synopses from the Aviation Safety Reporting System (ASRS) dataset. The comparison was facilitated by using embeddings from Large Language Models (LLMs), with aeroBERT demonstrating the highest similarity due to its aerospace-specific fine-tuning. A positive correlation was observed between synopsis length and their cosine similarity. In a subsequent phase, human factor issues involved in incidents as identified by ChatGPT were compared to human factor issues identified by safety analysts. A concurrence rate of 61% was found, with ChatGPT demonstrating a cautious approach towards attributing human factor issues. Finally, the model was used to attribute incidents to relevant parties. As no dedicated ground truth column existed for this task, a manual evaluation was conducted. ChatGPT attributed the majority of incidents to the Flight Crew, ATC, Ground Personnel, and Maintenance. This study opens new avenues for leveraging AI in aviation safety analysis.