相关论文: Coordinated pausing: An evaluation-based coordinat…
Recent and unremitting capability advances have been accompanied by calls for comprehensive, rather than patchwork, regulation of frontier artificial intelligence (AI). Approval regulation is emerging as a promising candidate. An approval…
As AI capabilities rapidly advance, the risk of catastrophic harm from large-scale training runs is growing. Yet the compute infrastructure that enables such development remains largely unregulated. This paper proposes a concrete framework…
The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might need to verify that powerful AI models are widely deployed…
Frontier AI developers operate at the intersection of rapid technical progress, extreme risk exposure, and growing regulatory scrutiny. While a range of external evaluations and safety frameworks have emerged, comparatively little attention…
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…
A Collaborative Artificial Intelligence System (CAIS) is a cyber-physical system that learns actions in collaboration with humans in a shared environment to achieve a common goal. In particular, a CAIS is equipped with an AI model to…
The recent development of powerful AI systems has highlighted the need for robust risk management frameworks in the AI industry. Although companies have begun to implement safety frameworks, current approaches often lack the systematic…
Safety frameworks have emerged as a best practice for managing risks from frontier artificial intelligence (AI) systems. However, it may be difficult for stakeholders to know if companies are adhering to their frameworks. This paper…
Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming. In this position paper, we argue that AI safety research should focus on human-centered evaluations that measure harmful…
As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…
The rapid advancement of AI systems has raised widespread concerns about potential harms of frontier AI systems and the need for responsible evaluation and oversight. In this position paper, we argue that frontier AI companies should report…
Enterprise AI Assistants are increasingly deployed in domains where accuracy is paramount, making each erroneous output a potentially significant incident. This paper presents a comprehensive framework for monitoring, benchmarking, and…
Frontier artificial intelligence (AI) systems pose increasing risks to society, making it essential for developers to provide assurances about their safety. One approach to offering such assurances is through a safety case: a structured,…
Several jurisdictions are starting to regulate frontier artificial intelligence (AI) systems, i.e. general-purpose AI systems that match or exceed the capabilities present in the most advanced systems. To reduce risks from these systems,…
Frontier AI companies first deploy their most advanced models internally, for weeks or months of safety testing, evaluation, and iteration, before a possible public release. For example, Anthropic recently developed a new class of model…
The increasing use of AI technologies has led to increasing AI incidents, posing risks and causing harm to individuals, organizations, and society. This study recognizes and addresses the lack of standardized protocols for reliably and…
To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations…
Artificial Intelligence (AI) systems have historically been used as tools that execute narrowly defined tasks. Yet recent advances in AI have unlocked possibilities for a new class of models that genuinely collaborate with humans in complex…
AI systems comprise a range of interactions across the technical and organisational components of a range of actors. These components work together to provide the systems' functionality. This socio-technical assemblage is increasingly…
Data is essential to train and fine-tune today's frontier artificial intelligence (AI) models and to develop future ones. To date, academic, legal, and regulatory work has primarily addressed how data can directly harm consumers and…