Related papers: Contemporary AI foundation models increase biologi…

Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but surgical benchmarks in particular are often missing from prominent medical benchmark suites. Since…

As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often simplistic, allowing models to perform uniformly well and making it difficult to…

The development of artificial general intelligence (AGI) is likely to be one of humanity's most consequential technological advancements. Leading AI labs and scientists have called for the global prioritization of AI safety citing…

Despite growing concerns about the risks of Generative AI (GenAI), there is limited understanding of public perceptions of these risks and their associated failure modes -- defined as recurring patterns of sociotechnical breakdown across…

Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regulation such as the EU AI Act. In this context, the black-box nature of machine learning models…

Modern Artificial Intelligence (AI) systems excel at diverse tasks, from image classification to strategy games, even outperforming humans in many of these domains. After making astounding progress in language learning in the recent decade,…

Prominent AI experts have suggested that companies developing high-risk AI systems should be required to show that such systems are safe before they can be developed or deployed. The goal of this paper is to expand on this idea and explore…

There is widespread optimism that frontier Large Language Models (LLMs) and LLM-augmented systems have the potential to rapidly accelerate scientific discovery across disciplines. Today, many benchmarks exist to measure LLM knowledge and…

When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…

Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that…

Foundation models, first introduced in 2021, refer to large-scale pretrained models (e.g., large language models (LLMs) and vision-language models (VLMs)) that learn from extensive unlabeled datasets through unsupervised methods, enabling…

This study systematically evaluates 27 frontier Large Language Models on eight biology benchmarks spanning molecular biology, genetics, cloning, virology, and biosecurity. Models from major AI developers released between November 2022 and…

Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na\"ive exposure of such capabilities fundamentally undermines modern…

Recent advances in machine learning, particularly the emergence of foundation models, are leading to new opportunities to develop technology-based solutions to societal problems. However, the reasoning and inner workings of today's complex…

Large language models (LLMs) are increasingly applied in biomedical domains, yet their reliability in drug-safety prediction remains underexplored. In this work, we investigate whether LLMs incorporate socio-demographic information into…

Large language models (LLMs) have shown remarkable success across many domains, yet their integration into cybersecurity applications remains limited due to a lack of general-purpose cybersecurity data, representational complexity, and…

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…

A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…

Artificial intelligence (AI) has been advancing at a fast pace and it is now poised for deployment in a wide range of applications, such as autonomous systems, medical diagnosis and natural language processing. Early adoption of AI…

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…