I am honoured to be chairing the delivery of the inaugural International Scientific Report on Advanced AI Safety. I am proud to publish this interim report which is the culmination of huge efforts by many experts over the six months since the work was commissioned at the Bletchley Park AI Safety Summit in November 2023. We know that advanced AI is developing very rapidly, and that there is considerable uncertainty over how these advanced AI systems might affect how we live and work in the future. AI has tremendous potential to change our lives for the better, but it also poses risks of harm. That is why having this thorough analysis of the available scientific literature and expert opinion is essential. The more we know, the better equipped we are to shape our collective destiny.

Local learning, which trains a network through layer-wise local targets and losses, has been studied as an alternative to backpropagation (BP) in neural computation. However, its algorithms often become more complex or require additional hyperparameters because of the locality, making it challenging to identify desirable settings in which the algorithm progresses in a stable manner. To provide theoretical and quantitative insights, we introduce the maximal update parameterization ($\mu$P) in the infinite-width limit for two representative designs of local targets: predictive coding (PC) and target propagation (TP). We verified that $\mu$P enables hyperparameter transfer across models of different widths. Furthermore, our analysis revealed unique and intriguing properties of $\mu$P that are not present in conventional BP. By analyzing deep linear networks, we found that PC's gradients interpolate between first-order and Gauss-Newton-like gradients, depending on the parameterization. We demonstrate that, in specific standard settings, PC in the infinite-width limit behaves more similarly to the first-order gradient. For TP, even with the standard scaling of the last layer, which differs from classical $\mu$P, its local loss optimization favors the feature learning regime over the kernel regime.

To understand the system-level interactions between the entities in Carbon Capture, Utilization, and Storage (CCUS), an agent-based foundational modeling tool, CCUS-Agent, is developed for a large-scale study of transportation flows and infrastructure in the United States. Key features of the tool include (i) modular design, (ii) multiple transportation modes, (iii) capabilities for extension, and (iv) testing against various system components and networks of small and large sizes. Five matching algorithms for CO2 supply agents (e.g., powerplants and industrial facilities) and demand agents (e.g., storage and utilization sites) are explored: Most Profitable First Year (MPFY), Most Profitable All Years (MPAY), Shortest Total Distance First Year (SDFY), Shortest Total Distance All Years (SDAY), and Shortest distance to long-haul transport All Years (ACAY). Before matching, the supply agent, demand agent, and route must be available, and the connection must be profitable. A profitable connection means the supply agent portion of revenue from the 45Q tax credit must cover the supply agent costs and all transportation costs, while the demand agent revenue portion must cover all demand agent costs. A case study employing over 5,500 supply and demand agents and multimodal CCUS transportation infrastructure in the contiguous United States is conducted. The results suggest that it is possible to capture over 9 billion tonnes (GT) of CO2 from 2025 to 2043, which will increase significantly to 22 GT if the capture costs are reduced by 40%. The MPFY and SDFY algorithms capture more CO2 earlier in the time horizon, while the MPAY and SDAY algorithms capture more later in the time horizon.

Recent advances in artificial intelligence (AI) have produced systems capable of increasingly sophisticated performance on cognitive tasks. However, AI systems still struggle in critical ways: unpredictable and novel environments (robustness), lack of transparency in their reasoning (explainability), challenges in communication and commitment (cooperation), and risks due to potential harmful actions (safety). We argue that these shortcomings stem from one overarching failure: AI systems lack wisdom. Drawing from cognitive and social sciences, we define wisdom as the ability to navigate intractable problems - those that are ambiguous, radically uncertain, novel, chaotic, or computationally explosive - through effective task-level and metacognitive strategies. While AI research has focused on task-level strategies, metacognition - the ability to reflect on and regulate one's thought processes - is underdeveloped in AI systems. In humans, metacognitive strategies such as recognizing the limits of one's knowledge, considering diverse perspectives, and adapting to context are essential for wise decision-making. We propose that integrating metacognitive capabilities into AI systems is crucial for enhancing their robustness, explainability, cooperation, and safety. By focusing on developing wise AI, we suggest an alternative to aligning AI with specific human values - a task fraught with conceptual and practical difficulties. Instead, wise AI systems can thoughtfully navigate complex situations, account for diverse human values, and avoid harmful actions. We discuss potential approaches to building wise AI, including benchmarking metacognitive abilities and training AI systems to employ wise reasoning. Prioritizing metacognition in AI research will lead to systems that act not only intelligently but also wisely in complex, real-world situations.

Social support, conveyed through a multitude of interactions and platforms such as social media, plays a pivotal role in fostering a sense of belonging, aiding resilience in the face of challenges, and enhancing overall well-being. This paper introduces Social Support Detection (SSD) as a Natural language processing (NLP) task aimed at identifying supportive interactions within online communities. The study presents the task of Social Support Detection (SSD) in three subtasks: two binary classification tasks and one multiclass task, with labels detailed in the dataset section. We conducted experiments on a dataset comprising 10,000 YouTube comments. Traditional machine learning models were employed, utilizing various feature combinations that encompass linguistic, psycholinguistic, emotional, and sentiment information. Additionally, we experimented with neural network-based models using various word embeddings to enhance the performance of our models across these subtasks.The results reveal a prevalence of group-oriented support in online dialogues, reflecting broader societal patterns. The findings demonstrate the effectiveness of integrating psycholinguistic, emotional, and sentiment features with n-grams in detecting social support and distinguishing whether it is directed toward an individual or a group. The best results for different subtasks across all experiments range from 0.72 to 0.82.

Machine unlearning--enabling a trained model to forget specific data--is crucial for addressing biased data and adhering to privacy regulations like the General Data Protection Regulation (GDPR)'s "right to be forgotten". Recent works have paid little attention to privacy concerns, leaving the data intended for forgetting vulnerable to membership inference attacks. Moreover, they often come with high computational overhead. In this work, we propose Pseudo-Probability Unlearning (PPU), a novel method that enables models to forget data efficiently and in a privacy-preserving manner. Our method replaces the final-layer output probabilities of the neural network with pseudo-probabilities for the data to be forgotten. These pseudo-probabilities follow either a uniform distribution or align with the model's overall distribution, enhancing privacy and reducing risk of membership inference attacks. Our optimization strategy further refines the predictive probability distributions and updates the model's weights accordingly, ensuring effective forgetting with minimal impact on the model's overall performance. Through comprehensive experiments on multiple benchmarks, our method achieves over 20% improvements in forgetting error compared to the state-of-the-art. Additionally, our method enhances privacy by preventing the forgotten set from being inferred to around random guesses.

Expert-driven frameworks for impact assessments (IAs) may inadvertently overlook the effects of AI technologies on the public's social behavior, policy, and the cultural and geographical contexts shaping the perception of AI and the impacts around its use. This research explores the potentials of fine-tuning LLMs on negative impacts of AI reported in a diverse sample of articles from 266 news domains spanning 30 countries around the world to incorporate more diversity into IAs. Our findings highlight (1) the potential of fine-tuned open-source LLMs in supporting IA of AI technologies by generating high-quality negative impacts across four qualitative dimensions: coherence, structure, relevance, and plausibility, and (2) the efficacy of small open-source LLM (Mistral-7B) fine-tuned on impacts from news media in capturing a wider range of categories of impacts that GPT-4 had gaps in covering.

The EcoCropsAID dataset is a comprehensive collection of 5,400 aerial images captured between 2014 and 2018 using the Google Earth application. This dataset focuses on five key economic crops in Thailand: rice, sugarcane, cassava, rubber, and longan. The images were collected at various crop growth stages: early cultivation, growth, and harvest, resulting in significant variability within each category and similarities across different categories. These variations, coupled with differences in resolution, color, and contrast introduced by multiple remote imaging sensors, present substantial challenges for land use classification. The dataset is an interdisciplinary resource that spans multiple research domains, including remote sensing, geoinformatics, artificial intelligence, and computer vision. The unique features of the EcoCropsAID dataset offer opportunities for researchers to explore novel approaches, such as extracting spatial and temporal features, developing deep learning architectures, and implementing transformer-based models. The EcoCropsAID dataset provides a valuable platform for advancing research in land use classification, with implications for optimizing agricultural practices and enhancing sustainable development. This study explicitly investigates the use of deep learning algorithms to classify economic crop areas in northeastern Thailand, utilizing satellite imagery to address the challenges posed by diverse patterns and similarities across categories.

For example, hundreds of millions of people utilize Twitter [22], Facebook [45, 46, 50], and Weibo [66] to record life events, express personal thoughts and opinions, and interact with friends every day. The openness of social media provides a spacious environment for content sharing while resulting in the disclosure of toxic content (toxicity), defined as "a rude, disrespectful, or unreasonable comment that is likely to make someone leave a discussion" [1], including hate speech [24], harassment [8, 22], insults and abuse [5], and offensive language [14], etc. Since the severe problem of context collapse [38], social media users are usually unaware of the disclosure of toxic content. For example, the prior studies [31, 36] found that about two-thirds of toxic content was implicit toxicity in online communities and the corresponding users were usually unaware of the content and the harm to others. Research revealed that 23.00% of users regret when they re-examine their shared content due to several reasons [58], such as lack of the consequence consideration of posts, culture misjudgment, unintended audience, misunderstanding of platform norms. To avoid toxic content disclosure, social media users generally conduct content censorship before publishing a post. The censorship procedure can be implemented by users themselves or by leveraging some automated tools. For example, several studies have found that individuals usually censored their content by checking, adjusting, or even deleting part of the content to make the content suitable to be published on social media [62]. Although there have been various censorship approaches, most of them focus on toxic content detection, e.g., toxicity score evaluation with Perspective

We introduce Constrained Human-AI Cooperation (CHAIC), an inclusive embodied social intelligence challenge designed to test social perception and cooperation in embodied agents. In CHAIC, the goal is for an embodied agent equipped with egocentric observations to assist a human who may be operating under physical constraints -- e.g., unable to reach high places or confined to a wheelchair -- in performing common household or outdoor tasks as efficiently as possible. To achieve this, a successful helper must: (1) infer the human's intents and constraints by following the human and observing their behaviors (social perception), and (2) make a cooperative plan tailored to the human partner to solve the task as quickly as possible, working together as a team (cooperative planning). To benchmark this challenge, we create four new agents with real physical constraints and eight long-horizon tasks featuring both indoor and outdoor scenes with various constraints, emergency events, and potential risks. We benchmark planning- and learning-based baselines on the challenge and introduce a new method that leverages large language models and behavior modeling. Empirical evaluations demonstrate the effectiveness of our benchmark in enabling systematic assessment of key aspects of machine social intelligence. Our benchmark and code are publicly available at https://github.com/UMass-Foundation-Model/CHAIC.