Related papers: The BIG Argument for AI Safety Cases

Ttraditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems which are acting in largely…

Complex decision-making by autonomous machines and algorithms could underpin the foundations of future society. Generative AI is emerging as a powerful engine for such transitions. However, we show that Generative AI-driven developments…

This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…

Assuring safety of artificial intelligence (AI) applied to safety-critical systems is of paramount importance. Especially since research in the field of automated driving shows that AI is able to outperform classical approaches, to handle…

Recent advancements in the field of Artificial Intelligence (AI) establish the basis to address challenging tasks. However, with the integration of AI, new risks arise. Therefore, to benefit from its advantages, it is essential to…

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…

Recent progress in artificial intelligence (AI) has drawn attention to the technology's transformative potential, including what some see as its prospects for causing large-scale harm. We review two influential arguments purporting to show…

This policy report draws on country studies from China, South Korea, Singapore, and the United Kingdom to identify effective tools and key barriers to interoperability in AI safety governance. It offers practical recommendations to support…

The integration of artificial intelligence (AI) into the industrial sector has not only driven innovation but also expanded the ethical landscape, necessitating a reevaluation of principles governing technology and its applications and…

Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by prominent AI companies to deter model misuse have disincentives…

In the past decade, the deployment of deep learning (Artificial Intelligence (AI)) methods has become pervasive across a spectrum of real-world applications, often in safety-critical contexts. This comprehensive research article rigorously…

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

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…

Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ensuring they operate in a safe and…

Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as…

Since the release of ChatGPT, there has been a lot of debate about whether AI systems pose an existential risk to humanity. This paper develops a general framework for thinking about the existential risk of AI systems. We analyze a two…

This study critically examines the commonly held assumption that explicability in artificial intelligence (AI) systems inherently boosts user trust. Utilizing a meta-analytical approach, we conducted a comprehensive examination of the…

Safety has become the central value around which dominant AI governance efforts are being shaped. Recently, this culminated in the publication of the International AI Safety Report, written by 96 experts of which 30 nominated by the…

AI-based systems are widely employed nowadays to make decisions that have far-reaching impacts on individuals and society. Their decisions might affect everyone, everywhere and anytime, entailing concerns about potential human rights…

As artificial intelligence (AI) and robotics increasingly permeate society, ensuring the ethical behavior of these systems has become paramount. This paper contends that transparency in AI decision-making processes is fundamental to…