Related papers: Evaluating AI Evaluation: Perils and Prospects
We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approaching AI risks. We…
Artificial Intelligence (AI) has burrowed into our lives in various aspects; however, without appropriate testing, deployed AI systems are often being criticized to fail in critical and embarrassing cases. Existing testing approaches mainly…
We review key considerations, practices, and areas for future work aimed at the responsible development and fielding of AI technologies. We describe critical challenges and make recommendations on topics that should be given priority…
Artificial Intelligence (AI) is a fast-growing research and development (R&D) discipline which is attracting increasing attention because of its promises to bring vast benefits for consumers and businesses, with considerable benefits…
For an artificial intelligence (AI) to be aligned with human values (or human preferences), it must first learn those values. AI systems that are trained on human behavior, risk miscategorising human irrationalities as human values -- and…
The use of Artificial Intelligence (AI), or more generally data-driven algorithms, has become ubiquitous in today's society. Yet, in many cases and especially when stakes are high, humans still make final decisions. The critical question,…
As Artificial Intelligence (AI) increasingly influences various aspects of society, there is growing public interest in its potential benefits and risks. In this paper we present results of public perception of AI from a survey conducted…
AI scientists powered by large language models have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these…
With increasing ubiquity of artificial intelligence (AI) in modern societies, individual countries and the international community are working hard to create an innovation-friendly, yet safe, regulatory environment. Adequate regulation is…
Current efforts in AI safety prioritize filtering harmful content, preventing manipulation of human behavior, and eliminating existential risks in cybersecurity or biosecurity. While pressing, this narrow focus overlooks critical…
The complexity of psychological principles underscore a significant societal challenge, given the vast social implications of psychological problems. Bridging the gap between understanding these principles and their actual clinical and…
Today, available methods that assess AI systems are focused on using empirical techniques to measure the performance of algorithms in some specific tasks (e.g., playing chess, solving mazes or land a helicopter). However, these methods are…
As frontier AI models become more capable, evaluating their potential to enable cyberattacks is crucial for ensuring the safe development of Artificial General Intelligence (AGI). Current cyber evaluation efforts are often ad-hoc, lacking…
Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these…
The integration of artificial intelligence (AI) technologies into judicial decision-making, particularly in pretrial, sentencing, and parole contexts, has generated substantial concerns about transparency, reliability, and accountability.…
Researchers are increasingly subjecting artificial intelligence systems to psychological testing. But to rigorously compare their cognitive capacities with humans and other animals, we must avoid both over- and under-stating our…
As a result of rapidly accelerating AI capabilities, over the past year, national governments and multinational bodies have announced efforts to address safety, security and ethics issues related to AI models. One high priority among these…
Artificial intelligence (AI) tools are being incorporated into scientific research workflows with the potential to enhance efficiency in tasks such as document analysis, question answering (Q&A), and literature search. However, system…
The rapid advancement of artificial intelligence (AI) technologies presents profound challenges to societal safety. As AI systems become more capable, accessible, and integrated into critical services, the dual nature of their potential is…
This paper summarizes the most cogent advantages and risks associated with Artificial Intelligence from an in-depth review of the literature. Then the authors synthesize the salient risk-related models currently being used in AI, technology…