A family member's hurried Google search for a last-second visa to visit New Zealand recently caused a headache--and provided a timely reminder of why Google faces a landmark US antitrust trial next week. Tapping on the first link took us off to a website that after a few swipes charged $118 for the necessary paperwork. Only later did it emerge that we'd paid a so-called "internet-based travel technology company" and not a government agency, and been fleeced for more than double the required cost. Fortunately, our panicked refund demand was fulfilled, but the miscue highlights a major frustration with Google that helped land it in court. The stacks of ads above its search results, like the visa link we clicked on, too often knock users off course from the information that they are seeking.

Back in 2016, a month before the EU referendum, I went along to the Future of Humanity Institute in Oxford to interview its director, the Swedish-born philosopher Nick Bostrom, who had just written a book called Superintelligence. The book outlined the existential risk to democracy and humanity implied by advances in machine learning. Bostrom's institute, which sought to weigh the apocalyptic potential of various humanity-threatening forces, had just been given a £1m grant by Elon Musk. If I think about that encounter, I remember three things. The first was that when I arrived a bed was being delivered to the institute, cementing the belief that anxiety about impending catastrophe was, these days, a 24/7 kind of occupation.

Lenore Skenazy's'free-range' parenting style is the basis of a new Utah law; she shares insight on'The Next Revolution.' Is there a "simple fix" to help quell kids' anxieties in an increasingly fast-paced and interconnected world? With the rise of the electronic world – social media, cable TV, 24-hour news – parents have adopted ways to protect children from unsafe spaces or disturbing content that makes kids more afraid or grow up too fast. But parents may have overcompensated, some argue. Perhaps parents led kids to their gradual decline in independence in recent decades, leading psychologist Dr. Camilo Ortiz and "Let Grow" nonprofit director Lenore Skenazy to ask "what if the problem was simply that kids are growing up so overprotected that they're scared of the world?" "If so, the solution would be simple, too," the duo wrote in a recent New York Times guest essay. "Start letting them do more things on their own."

Thomas Fuchs, the Dean of Artificial Intelligence and Human Health at Mount Sinai in NYC, said AI will be needed to retain the standard of care in the U.S. Microsoft is partnering with the digital pathology company Paige to build the world's largest image-based artificial intelligence (AI) model to help detect cancer, the companies announced. The AI model will be used for digital pathology and oncology, configured with billions of parameters to provide a computer vision AI that is orders of magnitude larger than any similar model existing today. Dr. Thomas Fuchs, Paige's founder and chief scientist, told FOX News Digital that the amount of data used in the model is "orders of magnitude" larger than anything made public by Google or Facebook. "It's so much larger than anything that has been published in that area ever," he said. That scale is essential for patients.

Ukraine has reported downing more than two dozen Russian drones over the country's capital, Kyiv, as Russia's defence ministry announced the destruction of eight Ukrainian drones near the annexed Crimean peninsula. The extent of the damage from the rival attacks early on Sunday was not immediately clear. Kyiv Mayor Vitali Klitschko said that at least one person was wounded in the city's historic Podil neighbourhood and a fire broke out near one of its parks. Debris from downed drones fell on the Darnytskyi, Solomianskyi, Shevchenkivskyi, Sviatoshynskyi and Podil districts, Klitschko and the city's military administration said. In the Shevchenkivskyi district, debris sparked a fire in an apartment, which was quickly distinguished.

The development of large high-quality datasets and high-performing models have led to significant advancements in the domain of Extractive Question Answering (EQA). This progress has sparked considerable interest in exploring unanswerable questions within the EQA domain. Training EQA models with unanswerable questions helps them avoid extracting misleading or incorrect answers for queries that lack valid responses. However, manually annotating unanswerable questions is labor-intensive. To address this, we propose AGent, a novel pipeline that automatically creates new unanswerable questions by re-matching a question with a context that lacks the necessary information for a correct answer. In this paper, we demonstrate the usefulness of this AGent pipeline by creating two sets of unanswerable questions from answerable questions in SQuAD and HotpotQA. These created question sets exhibit low error rates. Additionally, models fine-tuned on these questions show comparable performance with those fine-tuned on the SQuAD 2.0 dataset on multiple EQA benchmarks.

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on sequence-to-sequence (seq2seq) models, specifically machine translation models. We introduce algorithms that incorporate basic text perturbation heuristics and more advanced strategies, such as the gradient-based attack, which utilizes a differentiable approximation of the inherently non-differentiable translation metric. Through our investigation, we provide evidence that machine translation models display robustness displayed robustness against best performed known adversarial attacks, as the degree of perturbation in the output is directly proportional to the perturbation in the input. However, among underdogs, our attacks outperform alternatives, providing the best relative performance. Another strong candidate is an attack based on mixing of individual characters.

Accurate modeling of aircraft environmental impact is pivotal to the design of operational procedures and policies to mitigate negative aviation environmental impact. Aircraft environmental impact segmentation is a process which clusters aircraft types that have similar environmental impact characteristics based on a set of aircraft features. This practice helps model a large population of aircraft types with insufficient aircraft noise and performance models and contributes to better understanding of aviation environmental impact. Through measuring the similarity between aircraft types, distance metric is the kernel of aircraft segmentation. Traditional ways of aircraft segmentation use plain distance metrics and assign equal weight to all features in an unsupervised clustering process. In this work, we utilize weakly-supervised metric learning and partial information on aircraft fuel burn, emissions, and noise to learn weighted distance metrics for aircraft environmental impact segmentation. We show in a comprehensive case study that the tailored distance metrics can indeed make aircraft segmentation better reflect the actual environmental impact of aircraft. The metric learning approach can help refine a number of similar data-driven analytical studies in aviation.

Supervised learning models are challenged by the intrinsic complexities of training data such as outliers and minority subpopulations and intentional attacks at inference time with adversarial samples. While traditional robust learning methods and the recent adversarial training approaches are designed to handle each of the two challenges, to date, no work has been done to develop models that are robust with regard to the low-quality training data and the potential adversarial attack at inference time simultaneously. It is for this reason that we introduce Outlier Robust Adversarial Training (ORAT) in this work. ORAT is based on a bi-level optimization formulation of adversarial training with a robust rank-based loss function. Theoretically, we show that the learning objective of ORAT satisfies the $\mathcal{H}$-consistency in binary classification, which establishes it as a proper surrogate to adversarial 0/1 loss. Furthermore, we analyze its generalization ability and provide uniform convergence rates in high probability. ORAT can be optimized with a simple algorithm. Experimental evaluations on three benchmark datasets demonstrate the effectiveness and robustness of ORAT in handling outliers and adversarial attacks. Our code is available at https://github.com/discovershu/ORAT.

Prior work has explicated the coloniality of artificial intelligence (AI) development and deployment. One process that that work has not engaged with much is alignment: the tuning of large language model (LLM) behavior to be in line with desired values based on fine-grained human feedback. In addition to other practices, colonialism has a history of altering the beliefs and values of colonized peoples; this history is recapitulated in current LLM alignment practices. We suggest that AI alignment be decolonialized using three proposals: (a) changing the base moral philosophy from Western philosophy to dharma, (b) permitting traditions of argument and pluralism in alignment technologies, and (c) expanding the epistemology of values beyond instructions or commandments given in natural language.