Related papers: Evaluating Human-AI Safety: A Framework for Measur…
Artificial intelligence (AI) is interacting with people at an unprecedented scale, offering new avenues for immense positive impact, but also raising widespread concerns around the potential for individual and societal harm. Today, the…
This work establishes a foundational framework for standardizing AI evaluation RCTs (sometimes called human uplift studies). Drawing on established experimental practices from disciplines with established RCT traditions, including software…
Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI systems to pose catastrophic risks. Although numerous risks…
Artificial intelligence (AI) systems are deployed as collaborators in human decision-making. Yet, evaluation practices focus primarily on model accuracy rather than whether human-AI teams are prepared to collaborate safely and effectively.…
As Artificial Intelligence (AI) technologies continue to advance, protecting human autonomy and promoting ethical decision-making are essential to fostering trust and accountability. Human agency (the capacity of individuals to make…
This paper offers an overview of the prospects and ethics of using AI to achieve human enhancement, and more broadly what we call intellectual augmentation (IA). After explaining the central notions of human enhancement, IA, and AI, we…
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…
AI character platforms, which allow users to engage in conversations with AI personas, are a rapidly growing application domain. However, their immersive and personalized nature, combined with technical vulnerabilities, raises significant…
Well-designed technologies that offer high levels of human control and high levels of computer automation can increase human performance, leading to wider adoption. The Human-Centered Artificial Intelligence (HCAI) framework clarifies how…
Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a…
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…
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…
The complexity of dynamics in AI techniques is already approaching that of complex adaptive systems, thus curtailing the feasibility of formal controllability and reachability analysis in the context of AI safety. It follows that the…
The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a…
The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product…
All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deploy their models. Adoption of systematic approaches to risk…
Ensuring quality human-AI interaction (HAII) in safety-critical industries is essential. Failure to do so can lead to catastrophic and deadly consequences. Despite this urgency, existing research on HAII is limited, fragmented, and…
Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals. Increases in capabilities and autonomy may soon massively amplify…
Incident monitoring can drive safety improvements in high-reliability industries and population-scale technologies, but remains underdeveloped in AI governance. Public databases catalog thousands of AI incidents, but simple incident counts…
This paper presents an argument that certain AI safety measures, rather than mitigating existential risk, may instead exacerbate it. Under certain key assumptions - the inevitability of AI failure, the expected correlation between an AI…