相关论文: Modeling Transformative AI Risks (MTAIR) Project -…

Artificial Intelligence (AI) systems are increasingly used in high-stakes domains of our life, increasing the need to explain these decisions and to make sure that they are aligned with how we want the decision to be made. The field of…

AI systems are often introduced with high expectations, yet many fail to deliver, resulting in unintended harm and missed opportunities for benefit. We frequently observe significant "AI Mismatches", where the system's actual performance…

Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New training techniques that teach AI systems to reason step-by-step and inference-time enhancements have…

Artificial Intelligence (AI) algorithms are increasingly providing decision making and operational support across multiple domains. AI includes a wide library of algorithms for different problems. One important notion for the adoption of AI…

Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…

Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet researchers, policymakers, and technology companies lack shared terminology for discussing AI risks.…

Recent advances in artificial intelligence (AI) have led to a wide range of predictions about its long-term impact on humanity. A central focus is the potential emergence of transformative AI (TAI), eventually capable of outperforming…

Although AI systems are increasingly being leveraged to provide value to organizations, individuals, and society, significant attendant risks have been identified and have manifested. These risks have led to proposed regulations,…

Researchers, government bodies, and organizations have been repeatedly calling for a shift in the responsible AI community from general principles to tangible and operationalizable practices in mitigating the potential sociotechnical harms…

Modern general-purpose artificial intelligence (AI) systems present an urgent risk management challenge, as their rapidly evolving capabilities and potential for catastrophic harm outpace our ability to reliably assess their risks. Current…

World models - learned internal simulators of environment dynamics - are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic AI. By predicting future states in compressed latent spaces,…

Estimating catastrophic harms from frontier AI is hindered by deep ambiguity: many of its risks are not only unobserved but unanticipated by analysts. The central limitation of current risk analysis is the inability to populate the…

As artificial intelligence systems grow more capable and autonomous, frontier AI development poses potential systemic risks that could affect society at a massive scale. Current practices at many AI labs developing these systems lack…

Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set of approaches to…

Creating systems that are aligned with our goals is seen as a leading approach to create safe and beneficial AI in both leading AI companies and the academic field of AI safety. We defend the view that misaligned AGI - future, generally…

The malicious use or malfunction of advanced general-purpose AI (GPAI) poses risks that, according to leading experts, could lead to the 'marginalisation or extinction of humanity.' To address these risks, there are an increasing number of…

Evaluating AI safety requires statistically rigorous methods and risk metrics for understanding how the use of AI affects aggregated risk. However, much AI safety literature focuses upon risks arising from AI models in isolation, lacking…

This paper provides an overview and critique of the risk based model of artificial intelligence (AI) governance that has become a popular approach to AI regulation across multiple jurisdictions. The 'AI Policy Landscape in Europe, North…

Increasingly multi-purpose AI models, such as cutting-edge large language models or other 'general-purpose AI' (GPAI) models, 'foundation models,' generative AI models, and 'frontier models' (typically all referred to hereafter with the…

The systemic risks posed by general-purpose AI models are a growing concern, yet the effectiveness of mitigations remains underexplored. Previous research has proposed frameworks for risk mitigation, but has left gaps in our understanding…