Latvia and Romania, two member countries of the North Atlantic Treaty Organization (NATO), said Russian drones violated their airspace over the weekend in a move that could stoke boiling-hot tensions between Moscow and the military alliance. Latvia's government said Sunday a Russian drone had fallen over the east of the country the previous day, likely crossing in from Belarus. Separately, on Sunday, Romania's foreign ministry said "criminal" Russian airborne drones encroached on its airspace while targeting Ukraine's civilian infrastructure. Mircea Geoana, the outgoing deputy secretary general of NATO and Romania's former top diplomat, said the military alliance condemned Russia's violation of Romanian airspace. "While we have no information indicating an intentional attack by Russia against allies, these acts are irresponsible and potentially dangerous," he wrote on X, formerly Twitter.

Every fingerprint is believed to be unique, making it possible to identify an individual by matching a new fingerprint with an image on file, whether to unlock a mobile phone, access a bank account, or solve a murder. Fingerprint examiners, however, do not always agree on whether two print images match and, asked to recheck their work after several months, they sometimes do not even agree with themselves. That is leading to increased use of neural networks, powerhouses for identifying and matching patterns of all sorts, to automate and improve decisions about whether two fingerprints come from the same person. A group of computer scientists decided to use neural networks to test the assumption that no two fingerprints are the same. Using twin neural networks, researchers from Columbia University, Tufts University, and the State University of New York (SUNY) University at Buffalo looked for similarities between different fingerprints in a database from the National Institute of Standards and Technology (NIST).

NASA's Valkyrie robot, ready to be inhabited through virtual reality I am standing before one of the most advanced robots in the world and am awestruck and disoriented by its humanoid form. Part Transformer, part Star Wars stormtrooper and with hands that look like they can crush beer cans, at 1.8 metres tall and weighing 120 kilograms, NASA's Valkyrie robot is an intimidating figure. But it is the face that most transfixes me.

Apple is bringing sleep apnea detection to the most recent generations of its Watch, the company announced today. At the iPhones 16 launch event, Apple revealed the feature would come to the new Series 10, as well as the Series 9 and Ultra 2. If you wear your watch while you sleep, you'll get an alert in the morning if symptoms are detected through the night, urging you to visit your clinician. The data for this will be collated in the Health app on the iPhone. Rather than using oxygen saturation, which would be the logical approach, Apple says it's using motion tracking. This is likely related to the messy patent battle surrounding the blood oxygen sensor in the Watch that has stymied the company's work in this area.

Ukraine is adding little-known incendiary weapons to its armoury in its battle to fend off the ongoing Russian invasion, including "fire-spitting" drones reminiscent of dragons. On Wednesday, Ukraine's Defence Ministry posted videos on the social media platform X showing a Ukrainian drone raining down what appeared to be fire – but was molten metal – on forested positions presumed to be hiding Russian units. "A'dragon drone' in the direction of Kharkiv", the post from the ministry read, referring to Ukraine's second-largest city, which has been the target of repeated Russian bombing. Analysts say the weapon is a new and innovative introduction of an age-old weapon into the strategy of a Ukrainian military that has shown its growing proficiency in using small drones. Here's what to know about the new "dragon drones": Dragon drones carry a substance called thermite.

In 2015, Elon Musk and Sam Altman cofounded OpenAI based on a seemingly ethical ethos: to develop AI technology that benefits humanity, rather than systems controlled by big money corporations. Fast forward a decade that included a spectacular falling out between Musk and Altman, things look very different. Amid legal battles with his friend and former business partner, Musk's latest company, xAI, has launched its own powerful competitor, Grok AI. Described as "an AI search assistant with a twist of humor and a dash of rebellion," Grok is designed to have fewer guardrails than its major competitors. Unsurprisingly, Grok is prone to hallucinations and bias, with the AI assistant blamed for spreading misinformation about the 2024 election.

The gut-wrenching loss of an Ukraine Air Force F-16 chasing Iranian-made drones at low altitude last week is proof positive that Ukraine's air force is becoming more aggressive and capable. The daily air battles against missiles and drones over Ukraine are only a taste of what U.S. bases and allies could experience in the event of Chinese attacks. This I can tell you. Almost certainly, the pilot, identified as Col. Alexei "Moonfish" Mes, was being very aggressive in defense of his homeland. Russia had launched an attack on Ukraine with 127 missiles and 109 one-way attack drones on Aug. 26.

Latvia and Romania, NATO members who are allies of Ukraine, have said that Russian drones violated their airspace. Romania said a Russian drone entered its airspace during nighttime attacks across the Danube River in neighbouring Ukraine in the early hours of Sunday, while Latvia said one crashed in the eastern part of the country a day earlier. Romania's Ministry of National Defence said that Bucharest deployed F-16 fighter jets to monitor its airspace and that a search for the weapon's debris was under way at a potential crash site near the border. There were no immediate reports of casualties or damage. Bucharest strongly condemned the "renewed violation" brought on by Moscow's "illegal attacks".

The present paper is concerned with deep learning techniques applied to detection and localization of damage in a thin aluminum plate. We used data generated on a tabletop apparatus by mounting to the plate four piezoelectric transducers, each of which took turn to generate a Lamb wave that then traversed the region of interest before being received by the remaining three sensors. On training a neural network to analyze time-series data of the material response, which displayed damage-reflective features whenever the plate guided waves interacted with a contact load, we achieved a model that detected with greater than 99% accuracy in addition to a model that localized with $3.14 \pm 0.21$ mm mean distance error and captured more than 60% of test examples within the diffraction limit. For each task, the best-performing model was designed according to the inductive bias that our transducers were both similar and arranged in a square pattern on a nearly uniform plate.

Spatial disorientation is a leading cause of fatal aircraft accidents. This paper explores the potential of AI agents to aid pilots in maintaining balance and preventing unrecoverable losses of control by offering cues and corrective measures that ameliorate spatial disorientation. A multi-axis rotation system (MARS) was used to gather data from human subjects self-balancing in a spaceflight analog condition. We trained models over this data to create "digital twins" that exemplified performance characteristics of humans with different proficiency levels. We then trained various reinforcement learning and deep learning models to offer corrective cues if loss of control is predicted. Digital twins and assistant models then co-performed a virtual inverted pendulum (VIP) programmed with identical physics. From these simulations, we picked the 5 best-performing assistants based on task metrics such as crash frequency and mean distance from the direction of balance. These were used in a co-performance study with 20 new human subjects performing a version of the VIP task with degraded spatial information. We show that certain AI assistants were able to improve human performance and that reinforcement-learning based assistants were objectively more effective but rated as less trusted and preferable by humans.