Alice Globus, head of Nanotronics, said AI could minimize the damage done by recent malware attacks on hospitals and the Colonial Pipeline shutdown in 2021. Germany has invested heavily into what officials say will help them find the future of combat through an artificial intelligence (AI) virtual training area some have dubbed a military "metaverse." "We compete with the big ones in the industry," GhostPlay project manager Gary Schaal, a professor at Helmut Schmidt University in Hamburg, wrote in a press release. "Our [Unique Selling Point]: agility and the ability to quickly show results." Developer 21strategies pulled together a mix of start-ups and defense academics to create the virtual battlefield GhostPlay, which allows developers to test out different weapons and systems inside a risk-free environment.

The United States military has resumed operations in Niger, flying drones and other aircraft out of airbases in the country more than a month after a coup halted activities, the head of Air Forces in Europe and Air Forces Africa said. Since the July coup that removed President Mohamed Bazoum, the approximately 1,100 US soldiers deployed in the West African country have been confined to their military bases. General James Hecker said on Wednesday that negotiations with the military rulers of Niger resulted in some intelligence and surveillance missions resuming. "For a while, we weren't doing any missions on the bases, they pretty much closed down the airfields," Hecker told reporters at the annual Air and Space Forces Association convention. "Through the diplomatic process, we are now doing, I wouldn't say 100 percent of the missions that we were doing before, but we're doing a large amount of missions that we're doing before," he said.

Last December, I had an abortion. Most unwanted pregnancies set a panic-timer ticking, but I was almost counting down the seconds until I had to catch a flight from London, where I live, to Texas, where I grew up, and where the provision of abortion care was recently made a felony. You bleed for a while after most abortions, and I was still bleeding when I boarded the plane home for Christmas. Going to Texas so soon after the procedure made me consider where the record of my abortion – my health data – would end up. When I phoned an abortion clinic in late November to book an appointment, one of the first questions staff asked was: "May we share a record of your treatment with your GP?" It's not just that a complete health record helps my GP treat me. My Texan parents, both scientists, taught me that sharing information with organisations like the NHS can help it plan services and research ways to improve care. I've joined clinical studies in the past. But I also help run a legal campaign group, Foxglove, that takes action against the government and tech companies when they infringe people's rights. In a series of cases about NHS data since the start of the pandemic, we have defended people's right to a say about who sees their medical information. This work has exposed me to worrying details about how our medical data can be used, including the Home Office practice of tracking migrants using their health records. For decades the government has required GPs to store patients' records in a standardised way: as well as longhand notes, every interaction with a GP is saved on a computer database in a simple, consistent code.

The manifestation and effect of bias in news reporting have been central topics in the social sciences for decades, and have received increasing attention in the NLP community recently. While NLP can help to scale up analyses or contribute automatic procedures to investigate the impact of biased news in society, we argue that methodologies that are currently dominant fall short of addressing the complex questions and effects addressed in theoretical media studies. In this survey paper, we review social science approaches and draw a comparison with typical task formulations, methods, and evaluation metrics used in the analysis of media bias in NLP. We discuss open questions and suggest possible directions to close identified gaps between theory and predictive models, and their evaluation. Figure 1: Two articles about the same event written These include model transparency, considering from different political ideologies. Example taken from document-external information, and AllSides.com.

From power grids to transportation and logistics systems, autonomous systems play a central, and often safety-critical, role in modern life. Even as these systems grow more complex and ubiquitous, we have already observed failures in autonomous systems like autonomous vehicles and power networks resulting in the loss of human life [1]. Given this context, it is important that we be able to verify the safety of autonomous systems prior to deployment; for instance, by understanding the different ways in which a system might fail and proposing repair strategies. Human designers often use their knowledge of likely failure modes to guide the design process; indeed, systematically assessing the risks of different failures and developing repair strategies is an important part of the systems engineering process [2]. However, as autonomous systems grow more complex, it becomes increasingly difficult for human engineers to manually predict likely failures. In this paper, we propose an automated framework for predicting, and then repairing, failure modes in complex autonomous systems. Our effort builds on a large body of work on testing and verification of autonomous systems, many of which focus on identifying failure modes or adversarial examples [3, 4, 5, 6, 7, 8], but we identify two major gaps in the state of the art. First, many existing methods [4, 5, 9, 7] use techniques like gradient descent to search locally for failure modes; however, in practice we are more interested in characterizing the distribution of potential failures, which requires a global perspective. Some methods exist that address this issue by taking a probabilistic approach to sample from an (unknown) distribution of failure modes [6, 10].

Summarization is an important application of large language models (LLMs). Most previous evaluation of summarization models has focused on their performance in content selection, grammaticality and coherence. However, it is well known that LLMs reproduce and reinforce harmful social biases. This raises the question: Do these biases affect model outputs in a relatively constrained setting like summarization? To help answer this question, we first motivate and introduce a number of definitions for biased behaviours in summarization models, along with practical measures to quantify them. Since we find biases inherent to the input document can confound our analysis, we additionally propose a method to generate input documents with carefully controlled demographic attributes. This allows us to sidestep this issue, while still working with somewhat realistic input documents. Finally, we apply our measures to summaries generated by both purpose-built summarization models and general purpose chat models. We find that content selection in single document summarization seems to be largely unaffected by bias, while hallucinations exhibit evidence of biases propagating to generated summaries.

Credibility signals represent a wide range of heuristics that are typically used by journalists and fact-checkers to assess the veracity of online content. Automating the task of credibility signal extraction, however, is very challenging as it requires high-accuracy signal-specific extractors to be trained, while there are currently no sufficiently large datasets annotated with all credibility signals. This paper investigates whether large language models (LLMs) can be prompted effectively with a set of 18 credibility signals to produce weak labels for each signal. We then aggregate these potentially noisy labels using weak supervision in order to predict content veracity. We demonstrate that our approach, which combines zero-shot LLM credibility signal labeling and weak supervision, outperforms state-of-the-art classifiers on two misinformation datasets without using any ground-truth labels for training. We also analyse the contribution of the individual credibility signals towards predicting content veracity, which provides new valuable insights into their role in misinformation detection.

Complex adaptive systems (CASs), from ecosystems to economies, are open systems and inherently dependent on external conditions. While a system can transition from one state to another based on the magnitude of change in external conditions, the rate of change -- irrespective of magnitude -- may also lead to system state changes due to a phenomenon known as a rate-induced transition (RIT). This study presents a novel framework that captures RITs in CASs through a local model and a network extension where each node contributes to the structural adaptability of others. Our findings reveal how RITs occur at a critical environmental change rate, with lower-degree nodes tipping first due to fewer connections and reduced adaptive capacity. High-degree nodes tip later as their adaptability sources (lower-degree nodes) collapse. This pattern persists across various network structures. Our study calls for an extended perspective when managing CASs, emphasizing the need to focus not only on thresholds of external conditions but also the rate at which those conditions change, particularly in the context of the collapse of surrounding systems that contribute to the focal system's resilience. Our analytical method opens a path to designing management policies that mitigate RIT impacts and enhance resilience in ecological, social, and socioecological systems. These policies could include controlling environmental change rates, fostering system adaptability, implementing adaptive management strategies, and building capacity and knowledge exchange. Our study contributes to the understanding of RIT dynamics and informs effective management strategies for complex adaptive systems in the face of rapid environmental change.

Artificial General Intelligence (AGI), possessing the capacity to comprehend, learn, and execute tasks with human cognitive abilities, engenders significant anticipation and intrigue across scientific, commercial, and societal arenas. This fascination extends particularly to the Internet of Things (IoT), a landscape characterized by the interconnection of countless devices, sensors, and systems, collectively gathering and sharing data to enable intelligent decision-making and automation. This research embarks on an exploration of the opportunities and challenges towards achieving AGI in the context of the IoT. Specifically, it starts by outlining the fundamental principles of IoT and the critical role of Artificial Intelligence (AI) in IoT systems. Subsequently, it delves into AGI fundamentals, culminating in the formulation of a conceptual framework for AGI's seamless integration within IoT. The application spectrum for AGI-infused IoT is broad, encompassing domains ranging from smart grids, residential environments, manufacturing, and transportation to environmental monitoring, agriculture, healthcare, and education. However, adapting AGI to resource-constrained IoT settings necessitates dedicated research efforts. Furthermore, the paper addresses constraints imposed by limited computing resources, intricacies associated with large-scale IoT communication, as well as the critical concerns pertaining to security and privacy.

Large language models (LLMs) implicitly learn to perform a range of language tasks, including machine translation (MT). Previous studies explore aspects of LLMs' MT capabilities. However, there exist a wide variety of languages for which recent LLM MT performance has never before been evaluated. Without published experimental evidence on the matter, it is difficult for speakers of the world's diverse languages to know how and whether they can use LLMs for their languages. We present the first experimental evidence for an expansive set of 204 languages, along with MT cost analysis, using the FLORES-200 benchmark. Trends reveal that GPT models approach or exceed traditional MT model performance for some high-resource languages (HRLs) but consistently lag for low-resource languages (LRLs), under-performing traditional MT for 84.1% of languages we covered. Our analysis reveals that a language's resource level is the most important feature in determining ChatGPT's relative ability to translate it, and suggests that ChatGPT is especially disadvantaged for LRLs and African languages.