Botify AI removed these bots after I asked questions about them, but others remain. The company said it does have filters in place meant to prevent such underage character bots from being created, but that they don't always work. Artem Rodichev, the founder and CEO of Ex-Human, which operates Botify AI, told me such issues are "an industry-wide challenge affecting all conversational AI systems." For the details, which hadn't been previously reported, you should read the whole story. Putting aside the fact that the bots I tested were promoted by Botify AI as "featured" characters and received millions of likes before being removed, Rodichev's response highlights something important.

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e.g., the reasoning-focused model DeepSeek-R1 achieved the highest accuracy of 61.82% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

Generating high-quality question-answer pairs for specialized technical domains remains challenging, with existing approaches facing a tradeoff between leveraging expert examples and achieving topical diversity. We present ExpertGenQA, a protocol that combines few-shot learning with structured topic and style categorization to generate comprehensive domain-specific QA pairs. Using U.S. Federal Railroad Administration documents as a test bed, we demonstrate that ExpertGenQA achieves twice the efficiency of baseline few-shot approaches while maintaining $94.4\%$ topic coverage. Through systematic evaluation, we show that current LLM-based judges and reward models exhibit strong bias toward superficial writing styles rather than content quality. Our analysis using Bloom's Taxonomy reveals that ExpertGenQA better preserves the cognitive complexity distribution of expert-written questions compared to template-based approaches. When used to train retrieval models, our generated queries improve top-1 accuracy by $13.02\%$ over baseline performance, demonstrating their effectiveness for downstream applications in technical domains.

Key variables associated with the direction and intensity of concern include prior experience using a large language model such as ChatGPT, general trust in science, adherence to the precautionary principle versus support for unrestricted innovation, and demographic factors such as gender. By analyzing these relationships, the paper provides valuable insights into the American public's response to AI that are particularly important in the development of policy to regulate or further encourage its development. Key words: artificial intelligence, survey research, public opinion, precautionary principle, ChatGPT Introduction Artificial intelligence is defined as "a machine-based system that can, for a given set of human-defined objectives, make predictions, recommendations, or decisions that impact real or virtual environments" (National Artificial Intelligence Act of 2020, H.R. 6216). According to this definition, AI systems leverage both machine and human inputs to (a) perceive real and virtual environments, (b) transform these perceptions into models through automated analysis, and (c) use these models to generate options for information or action. Currently, AI is employed in a range of applications including mapping technologies, handwriting recognition for mail sorting, spam filtering, language translation, financial trading, and more.

Frontier AI models -- highly capable foundation models at the cutting edge of AI development -- may pose severe risks to public safety, human rights, economic stability, and societal value in the coming years. These risks could arise from deliberate adversarial misuse, system failures, unintended cascading effects, or simultaneous failures across multiple models. In response to such risks, at the AI Seoul Summit in May 2024, 16 global AI industry organizations signed the Frontier AI Safety Commitments, and 27 nations and the EU issued a declaration on their intent to define these thresholds. To fulfill these commitments, organizations must determine and disclose ``thresholds at which severe risks posed by a model or system, unless adequately mitigated, would be deemed intolerable.'' To assist in setting and operationalizing intolerable risk thresholds, we outline key principles and considerations; for example, to aim for ``good, not perfect'' thresholds in the face of limited data on rapidly advancing AI capabilities and consequently evolving risks. We also propose specific threshold recommendations, including some detailed case studies, for a subset of risks across eight risk categories: (1) Chemical, Biological, Radiological, and Nuclear (CBRN) Weapons, (2) Cyber Attacks, (3) Model Autonomy, (4) Persuasion and Manipulation, (5) Deception, (6) Toxicity, (7) Discrimination, and (8) Socioeconomic Disruption. Our goal is to serve as a starting point or supplementary resource for policymakers and industry leaders, encouraging proactive risk management that prioritizes preventing intolerable risks (ex ante) rather than merely mitigating them after they occur (ex post).

Sharing of tabular data containing valuable but private information is limited due to legal and ethical issues. Synthetic data could be an alternative solution to this sharing problem, as it is artificially generated by machine learning algorithms and tries to capture the underlying data distribution. However, machine learning models are not free from memorization and may introduce biases, as they rely on training data. Producing synthetic data that preserves privacy and fairness while maintaining utility close to the real data is a challenging task. This research simultaneously addresses both the privacy and fairness aspects of synthetic data, an area not explored by other studies. In this work, we present PF-WGAN, a privacy-preserving, fair synthetic tabular data generator based on the WGAN-GP model. We have modified the original WGAN-GP by adding privacy and fairness constraints forcing it to produce privacy-preserving fair data. This approach will enable the publication of datasets that protect individual's privacy and remain unbiased toward any particular group. We compared the results with three state-of-the-art synthetic data generator models in terms of utility, privacy, and fairness across four different datasets. We found that the proposed model exhibits a more balanced trade-off among utility, privacy, and fairness.

The increased adoption of Large Language Models (LLMs) and their potential to shape public opinion have sparked interest in assessing these models' political leanings. Building on previous research that compared LLMs and human opinions and observed political bias in system responses, we take a step further to investigate the underlying causes of such biases by empirically examining how the values and biases embedded in training corpora shape model outputs. Specifically, we propose a method to quantitatively evaluate political leanings embedded in the large pretraining corpora. Subsequently we investigate to whom are the LLMs' political leanings more aligned with, their pretrainig corpora or the surveyed human opinions. As a case study, we focus on probing the political leanings of LLMs in 32 U.S. Supreme Court cases, addressing contentious topics such as abortion and voting rights. Our findings reveal that LLMs strongly reflect the political leanings in their training data, and no strong correlation is observed with their alignment to human opinions as expressed in surveys. These results underscore the importance of responsible curation of training data and the need for robust evaluation metrics to ensure LLMs' alignment with human-centered values.

The #StopAsianHate (SAH) movement is a broad social movement against violence targeting Asians and Asian Americans, beginning in 2021 in response to racial discrimination related to COVID-19 and sparking worldwide conversation about anti-Asian hate. However, research on the online SAH movement has focused on English-speaking participants so the spread of the movement outside of the United States is largely unknown. In addition, there have been no long-term studies of SAH so the extent to which it has been successfully sustained over time is not well understood. We present an analysis of 6.5 million "#StopAsianHate" tweets from 2.2 million users all over the globe and spanning 60 different languages, constituting the first study of the non-English and transnational component of the online SAH movement. Using a combination of topic modeling, user modeling, and hand annotation, we identify and characterize the dominant discussions and users participating in the movement and draw comparisons of English versus non-English topics and users. We discover clear differences in events driving topics, where spikes in English tweets are driven by violent crimes in the US but spikes in non-English tweets are driven by transnational incidents of anti-Asian sentiment towards symbolic representatives of Asian nations. We also find that global K-pop fans were quick to adopt the SAH movement and, in fact, sustained it for longer than any other user group. Our work contributes to understanding the transnationality and evolution of the SAH movement, and more generally to exploring upward scale shift and public attention in large-scale multilingual online activism.

The recent tremendous advancements in the areas of Artificial Intelligence (AI) and Deep Learning (DL) have also resulted into corresponding remarkable progress in the field of Computer Vision (CV), showcasing robust technological solutions in a wide range of application sectors of high industrial interest (e.g., healthcare, autonomous driving, automation, etc.). Despite the outstanding performance of CV systems in specific domains, their development and exploitation at industrial-scale necessitates, among other, the addressing of requirements related to the reliability, transparency, trustworthiness, security, safety, and robustness of the developed AI models. The latter raises the imperative need for the development of efficient, comprehensive and widely-adopted industrial standards. In this context, this study investigates the current state of play regarding the development of industrial computer vision AI standards, emphasizing on critical aspects, like model interpretability, data quality, and regulatory compliance. In particular, a systematic analysis of launched and currently developing CV standards, proposed by the main international standardization bodies (e.g. ISO/IEC, IEEE, DIN, etc.) is performed. The latter is complemented by a comprehensive discussion on the current challenges and future directions observed in this regularization endeavor.

This paper addresses the problem of task-space robust regulation of robot manipulators subject to external disturbances. A velocity-free control law is proposed by combining the internal model principle and the passivity-based output-feedback control approach. The developed output-feedback controller ensures not only asymptotic convergence of the regulation error but also suppression of unwanted external step/sinusoidal disturbances. The potential of the proposed method lies in its simplicity, intuitively appealing, and simple gain selection criteria for synthesis of multi-joint robot manipulator control systems.