Feedback is New Scientist's popular sideways look at the latest science and technology news. You can submit items you believe may amuse readers to Feedback by emailing feedback@newscientist.com Some things are sadly inevitable: death, taxes, another Coldplay album. One such inevitability, long since proved beyond any reasonable doubt, is that if you try to suppress an embarrassing story, you will only draw more attention to it. This phenomenon is called the Streisand Effect, after an incident in 2003 when Barbra Streisand sued to have an aerial photograph taken off the internet.

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvements, the importance of prompt-data construction has been overlooked. This paper addresses this gap by exploring data-driven bottlenecks in RLHF performance scaling, particularly reward hacking and decreasing response diversity. We introduce a hybrid reward system combining reasoning task verifiers (RTV) and a generative reward model (GenRM) to mitigate reward hacking. We also propose a novel prompt-selection method, Pre-PPO, to maintain response diversity and enhance learning effectiveness. Additionally, we find that prioritizing mathematical and coding tasks early in RLHF training significantly improves performance. Experiments across two model sizes validate our methods' effectiveness and scalability. Results show that RTV is most resistant to reward hacking, followed by GenRM with ground truth, and then GenRM with SFT Best-of-N responses. Our strategies enable rapid capture of subtle task-specific distinctions, leading to substantial improvements in overall RLHF performance. This work highlights the importance of careful data construction and provides practical methods to overcome performance barriers in RLHF.

A March 20 article in The Atlantic served as the letter's impetus. It reported that Meta had used LibGen, a pirated collection of over 7.5 million books, to train its AI models. Anyone on the internet over the last few weeks has likely seen videos of distraught authors learning that their work is available on the database (and potentially used by Meta without their permission). A lawsuit in the US alleges Meta CEO Mark Zuckerberg approved the use of LibGen's data to train its AI. The lawsuit's plaintiffs include writers Sarah Silverman and Ta-Nehisi Coates.

Cooper is an open-source package for solving constrained optimization problems involving deep learning models. Cooper implements several Lagrangian-based first-order update schemes, making it easy to combine constrained optimization algorithms with high-level features of PyTorch such as automatic differentiation, and specialized deep learning architectures and optimizers. Although Cooper is specifically designed for deep learning applications where gradients are estimated based on mini-batches, it is suitable for general non-convex continuous constrained optimization. Cooper's source code is available at https://github.com/cooper-org/cooper.

In this work, we analyze video data and interviews from a public deployment of two trash barrel robots in a large public space to better understand the sensemaking activities people perform when they encounter robots in public spaces. Based on an analysis of 274 human-robot interactions and interviews with N=65 individuals or groups, we discovered that people were responding not only to the robots or their behavior, but also to the general idea of deploying robots as trashcans, and the larger social implications of that idea. They wanted to understand details about the deployment because having that knowledge would change how they interact with the robot. Based on our data and analysis, we have provided implications for design that may be topics for future human-robot design researchers who are exploring robots for public space deployment. Furthermore, our work offers a practical example of analyzing field data to make sense of robots in public spaces.

Machine unlearning, which enables a model to forget specific data upon request, is increasingly relevant in the era of privacy-centric machine learning, particularly within federated learning (FL) environments. This paper presents a pioneering study on benchmarking machine unlearning methods within a federated setting for tabular data, addressing the unique challenges posed by cross-silo FL where data privacy and communication efficiency are paramount. We explore unlearning at the feature and instance levels, employing both machine learning, random forest and logistic regression models. Our methodology benchmarks various unlearning algorithms, including fine-tuning and gradient-based approaches, across multiple datasets, with metrics focused on fidelity, certifiability, and computational efficiency. Experiments demonstrate that while fidelity remains high across methods, tree-based models excel in certifiability, ensuring exact unlearning, whereas gradient-based methods show improved computational efficiency. This study provides critical insights into the design and selection of unlearning algorithms tailored to the FL environment, offering a foundation for further research in privacy-preserving machine learning.

Abstract: The research introduces a multi - agent simulation that uses fuzzy inference to investigate the work distribution and battery charging control of mobile baggage conveyor robots in an airport in a comprehensive manner. Thanks to a distributed system, this simulation approach provides high adaptability, adjusting to changes in conveyor agent availability, battery capacity, awareness of the activities of the conveyor fleet, and knowledge of the context of infrastructure resource availability. Dynamic factors, such as workload variations and communication between the conveyor agents and infrastructure are con sidered as heuristics, hig hlighting the importance of flexible and collaborative approaches in autonomous systems. The results highlight the effectiveness of adaptive fuzzy multi - agent models to optimize dynamic task allocation, adapt to the variation of baggage arrival flows, impr ove the overall operational efficiency of conveyor agents, and reduce their energy consumption. Keywords: autonomous industrial vehicle, agent - based si mulation, fuzzy agent, dynamic task allocation, battery charge management, Airport 4.0 1. INTRODUCTION The implementation of fleets of Autonomous Industrial Vehicles (AIV) in the context of Airport 4.0 presents a number of challenges, all of which are connected to the true degree of autonomy of these vehicles: employee acceptance, vehicle localization, traf fic flow, failure detection, collision avoidance, and vehicle perception in dynamic environments. The different limitations and specifications developed by producers and potential consumers of these AIVs might be taken into consideration thanks to simulati on.

State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Consequently, Content Removal Techniques (CRTs) have emerged as a growing area of research to control outputs without full-scale retraining. Recent work has explored the use of Machine Unlearning in generative models to address content removal. However, the focus of such research has been on diffusion models, and unlearning in Generative Adversarial Networks (GANs) has remained largely unexplored. We address this gap by proposing Text-to-Unlearn, a novel framework that selectively unlearns concepts from pre-trained GANs using only text prompts, enabling feature unlearning, identity unlearning, and fine-grained tasks like expression and multi-attribute removal in models trained on human faces. Leveraging natural language descriptions, our approach guides the unlearning process without requiring additional datasets or supervised fine-tuning, offering a scalable and efficient solution. To evaluate its effectiveness, we introduce an automatic unlearning assessment method adapted from state-of-the-art image-text alignment metrics, providing a comprehensive analysis of the unlearning methodology. To our knowledge, Text-to-Unlearn is the first cross-modal unlearning framework for GANs, representing a flexible and efficient advancement in managing generative model behavior.

--Artificial intelligence (AI) trends vary significantly across global regions, shaping the trajectory of innovation, regulation, and societal impact. This variation influences how dif - ferent regions approach AI development, balancing technological progress with ethical and regulatory considerations. This study conducts a comparative analysis of AI trends in the United States (US), the European Union (EU), and Asia, focusing on three key dimensions: generative AI, ethical oversight, and industrial applications. The US prioritizes market -driven innovation with minimal regulatory constraints, the EU enforces a precautionary risk -based framework emphasizing ethical safeguards, and Asia employs state -guided AI strategies that balance rapid deployment with regulatory oversight. Although these approaches reflect different economic models and policy priorities, their divergence poses challenges to international collaboration, regulatory harmonization, and the development of global AI standards. To address these challenges, this paper synthesizes regional strengths to propose an adaptive AI governance framework that integrates risk -tiered oversight, innovation accelerators, and strategic alignment mechanisms. By bridging governance gaps, this study offers actionable insights for fostering responsible AI development while ensuring a balance between technological progress, ethical imperatives, and regulatory coherence. Artificial intelligence (AI) has emerged as a transformative force in the 21st century, reshaping industries, governance structures, and societal interactions at an unprecedented pace. From generative AI creating human - like text and images to autonomous systems revolutionizing healthcare, finance, and manufacturing, AI's influence is profound and far - reaching.

As large language models (LLMs) advance, efficient knowledge evaluation becomes crucial to verifying their capabilities. Traditional methods, relying on benchmarks, face limitations such as high resource costs and information loss. We propose the Large-scale Reference-based Efficient Knowledge Evaluation for Large Language Model (RECKON), which directly uses reference data to evaluate models. RECKON organizes unstructured data into manageable units and generates targeted questions for each cluster, improving evaluation accuracy and efficiency. Experimental results show that RECKON reduces resource consumption by 56.5% compared to traditional methods while achieving over 97% accuracy across various domains, including world knowledge, code, legal, and biomedical datasets. Code is available at https://github.com/MikeGu721/reckon