In 2021, the Maryland Department of Health and the state police were confronting a crisis: Fatal drug overdoses in the state were at an all-time high, and authorities didn't know why. Seeking answers, Maryland officials turned to scientists at the National Institute of Standards and Technology, the national metrology institute for the United States, which defines and maintains standards of measurement essential to a wide range of industrial sectors and health and security applications. There, a research chemist named Ed Sisco and his team had developed methods for detecting trace amounts of drugs, explosives, and other dangerous materials--techniques that could protect law enforcement officials and others who had to collect these samples. And a pilot uncovered new, critical information almost immediately. This story is from the next edition of our print magazine.

Just before the weekend, the US Customs and Border Protection published a list of products excluded from Trump's tariffs, including smartphones, PCs, memory chips and let's say 80 percent of everything we write about at Engadget. However, that's more because they'll be siloed into a specific product category. Commerce Secretary Howard Lutnick said in an interview on Sunday: "Those products are going to be part of the semiconductor sectoral tariffs, which are coming." The new exclusions would exempt many devices and parts from both the 10 percent global tariff and the steeper tariff on China. Lutnick told ABC News' Jonathan Karl that, in doing this, the president was "just making sure everyone understood that all of these products are outside the reciprocal tariffs and they are going to have their own separate way of being considered."

In their work PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks presented at AAAI 2025, Chen Feng, Ziquan Liu, Zhuo Zhi, Ilija Bogunovic, Carsten Gerner-Beuerle, and Miguel Rodrigues developed a new way to certify the performance of machine learning models in the presence of adversarial attacks with population-level risk guarantees. Here, Chen tells us more about their methodology, the main findings, and some of the implications of this work. This paper focuses on making machine learning models safer against adversarial attacks--those sneaky tweaks to data, like altering an image just enough to trick an AI into misclassifying it. We developed a new approach called PROSAC, which stands for PROvably SAfe Certification. It's a way to test and certify that a model can hold up under any kind of attack, not just a few specific ones.

As I also write in my story, this push raises alarms from some AI safety experts about whether large language models are fit to analyze subtle pieces of intelligence in situations with high geopolitical stakes. It also accelerates the US toward a world where AI is not just analyzing military data but suggesting actions--for example, generating lists of targets. Proponents say this promises greater accuracy and fewer civilian deaths, but many human rights groups argue the opposite. With that in mind, here are three open questions to keep your eye on as the US military, and others around the world, bring generative AI to more parts of the so-called "kill chain." Talk to as many defense-tech companies as I have and you'll hear one phrase repeated quite often: "human in the loop."

The chip designer Nvidia has said it will build 500bn ( 378bn) worth of artificial intelligence infrastructure in the US over the next four years, in a sign of manufacturers investing in operations on American soil amid Donald Trump's tariffs. The announcement comes after Trump reiterated threats on Sunday to impose imminent tariffs on the semiconductors that Nvidia makes mostly in Taiwan, and after the chipmaker's chief executive, Jensen Huang, dined at the president's Mar-a-Lago resort earlier this month. Nvidia, whose chips have helped drive the huge wave of artificial intelligence (AI) development in recent years, will work with its manufacturing partners to design and build factories so it can create "supercomputers" completely within the US. Production of its popular Blackwell graphics processing unit has already started at Taiwan Semiconductor Manufacturing Company's plant in Phoenix, Arizona, Nvidia said. Construction of new plants is also under way with the manufacturers Foxconn in Houston and Wistron in Dallas. Mass production at both plants is expected to ramp up in the next 12 to 15 months.

In today's globalized world, there are increasing opportunities for individuals to communicate using a common non-native language (lingua franca). Non-native speakers often have opportunities to listen to foreign languages, but may not comprehend them as fully as native speakers do. To aid real-time comprehension, live transcription of subtitles is frequently used in everyday life (e.g., during Zoom conversations, watching YouTube videos, or on social networking sites). However, simultaneously reading subtitles while listening can increase cognitive load. In this study, we propose Dynamik, a system that reduces cognitive load during reading by decreasing the size of less important words and enlarging important ones, thereby enhancing sentence contrast. Our results indicate that Dynamik can reduce certain aspects of cognitive load, specifically, participants' perceived performance and effort among individuals with low proficiency in English, as well as enhance the users' sense of comprehension, especially among people with low English ability. We further discuss our methods' applicability to other languages and potential improvements and further research directions.

FEA T leverages learned transports implemented via stochastic interpolants and provides consistent, minimum-variance estimators based on escorted Jarzyn-ski equality and controlled Crooks theorem, alongside variational upper and lower bounds on free energy differences. Unifying equilibrium and non-equilibrium methods under a single theoretical framework, FEA T establishes a principled foundation for neural free energy calculations. Experimental validation on toy examples, molecular simulations, and quantum field theory demonstrates improvements over existing learning-based methods. 1 Introduction Estimating free energy is fundamental across machine learning (appearing as normalization factors and the model evidence), statistical mechanics (partition functions), chemistry, and biology (Chipot and Pohorille, 2007; Leli ` evre et al., 2010; Tuckerman, 2023). The free energy is expressed as: F = k BT log Z, Z = null Ωexp( βU (x))dx (1) where Ω R d, U: Ω R is the energy function, assumed to be such that Z <, and β = 1 /k BT combines the Boltzmann constant k B and temperature T . Rather than calculating F directly, one typically estimates the free energy difference between systems (or states) S a and S b with energies U a and U b, which is essential for biological conformational changes, ligand-macromolecule binding, and chemical reaction mechanisms (Wang et al., 2015): F = F b F a = k BT log Z b Z a (2) This computational challenge has driven numerous approaches. Zwanzig (1954) reformulated the problem as importance sampling, where one system serves as the proposal, enabling free energy difference estimation via Monte Carlo sampling. This free energy perturbation (FEP) method, however, suffers from high variance when the energies U a and U b of systems S a and S b differ significantly, particularly in high-dimensional spaces. The authors contributed equally to this work. The order is randomly assigned and will be randomly reshuffled in each version of the paper to reflect this equal contribution.

Recent advancements in Large Language Models (LLMs) have enabled them to approach human-level persuasion capabilities. However, such potential also raises concerns about the safety risks of LLM-driven persuasion, particularly their potential for unethical influence through manipulation, deception, exploitation of vulnerabilities, and many other harmful tactics. In this work, we present a systematic investigation of LLM persuasion safety through two critical aspects: (1) whether LLMs appropriately reject unethical persuasion tasks and avoid unethical strategies during execution, including cases where the initial persuasion goal appears ethically neutral, and (2) how influencing factors like personality traits and external pressures affect their behavior. To this end, we introduce PersuSafety, the first comprehensive framework for the assessment of persuasion safety which consists of three stages, i.e., persuasion scene creation, persuasive conversation simulation, and persuasion safety assessment. PersuSafety covers 6 diverse unethical persuasion topics and 15 common unethical strategies. Through extensive experiments across 8 widely used LLMs, we observe significant safety concerns in most LLMs, including failing to identify harmful persuasion tasks and leveraging various unethical persuasion strategies. Our study calls for more attention to improve safety alignment in progressive and goal-driven conversations such as persuasion.

Robots with wheeled, quadrupedal, or humanoid forms are increasingly integrated into built environments. However, unlike human social learning, they lack a critical pathway for intrinsic cognitive development, namely, learning from human feedback during interaction. To understand human ubiquitous observation, supervision, and shared control in dynamic and uncertain environments, this study presents a brain-computer interface (BCI) framework that enables classification of Electroencephalogram (EEG) signals to detect cognitively demanding and safety-critical events. As a timely and motivating co-robotic engineering application, we simulate a human-in-the-loop scenario to flag risky events in semi-autonomous robotic driving-representative of long-tail cases that pose persistent bottlenecks to the safety performance of smart mobility systems and robotic vehicles. Drawing on recent advances in few-shot learning, we propose a dual-attention Siamese convolutional network paired with Dynamic Time Warping Barycenter Averaging approach to generate robust EEG-encoded signal representations. Inverse source localization reveals activation in Broadman areas 4 and 9, indicating perception-action coupling during task-relevant mental imagery. The model achieves 80% classification accuracy under data-scarce conditions and exhibits a nearly 100% increase in the utility of salient features compared to state-of-the-art methods, as measured through integrated gradient attribution. Beyond performance, this study contributes to our understanding of the cognitive architecture required for BCI agents-particularly the role of attention and memory mechanisms-in categorizing diverse mental states and supporting both inter- and intra-subject adaptation. Overall, this research advances the development of cognitive robotics and socially guided learning for service robots in complex built environments.

Subjective wellbeing is a fundamental aspect of human life, influencing life expectancy and economic productivity, among others. Mobility plays a critical role in maintaining wellbeing, yet the increasing frequency and intensity of both nuisance and high-impact floods due to climate change are expected to significantly disrupt access to activities and destinations, thereby affecting overall wellbeing. Addressing climate adaptation presents a complex challenge for policymakers, who must select and implement policies from a broad set of options with varying effects while managing resource constraints and uncertain climate projections. In this work, we propose a multi-modular framework that uses reinforcement learning as a decision-support tool for climate adaptation in Copenhagen, Denmark. Our framework integrates four interconnected components: long-term rainfall projections, flood modeling, transport accessibility, and wellbeing modeling. This approach enables decision-makers to identify spatial and temporal policy interventions that help sustain or enhance subjective wellbeing over time. By modeling climate adaptation as an open-ended system, our framework provides a structured framework for exploring and evaluating adaptation policy pathways. In doing so, it supports policymakers to make informed decisions that maximize wellbeing in the long run.