Related papers: Position Paper: Bounded Alignment: What (Not) To E…

The use of artificial intelligence (AI) and AI methods in the workplace holds both great opportunities as well as risks to occupational safety and discrimination. In addition to legal regulation, technical standards will play a key role in…

As the capabilities of large machine learning models continue to grow, and as the autonomy afforded to such models continues to expand, the spectre of a new adversary looms: the models themselves. The threat that a model might behave in a…

Instruction-tuned Large Language Models (LLMs) are increasingly deployed as AI Assistants in firms for support in cognitive tasks. These AI assistants carry embedded perspectives which influence factors across the firm including…

A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally,…

Artificial Intelligence (AI) agents capable of autonomous learning and independent decision-making hold great promise for addressing complex challenges across various critical infrastructure domains, including transportation, energy…

We consider that existing approaches to AI "safety" and "alignment" may not be using the most effective tools, teams, or approaches. We suggest that an alternative and better approach to the problem may be to treat alignment as a social…

The proliferation of agentic artificial intelligence systems--characterized by autonomous goal-seeking, tool use, and multi-agent coordination--presents unprecedented challenges to existing legal and financial regulatory frameworks. While…

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…

As general-purpose artificial intelligence systems become increasingly integrated into society and are used for information seeking, content generation, problem solving, textual analysis, coding, and running processes, it is crucial to…

Pluralistic alignment is concerned with ensuring that an AI system's objectives and behaviors are in harmony with the diversity of human values and perspectives. In this paper we study the notion of pluralistic alignment in the context of…

Edge AI is often framed as model compression and deployment under tight constraints. We argue a stronger operational thesis: Edge AI in realistic deployments is necessarily adaptive. In long-horizon operation, a fixed (non-adaptive)…

As AI systems become embedded in everyday practice, value misalignment has emerged as a pressing concern. Yet, dominant alignment approaches remain model centric, treating users as passive recipients of prespecified values rather than as…

The value alignment problem for artificial intelligence (AI) is often framed as a purely technical or normative challenge, sometimes focused on hypothetical future systems. I argue that the problem is better understood as a structural…

The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a…

Frontier AI both amplifies existing risks and introduces qualitatively novel challenges. Not only is there a notable lack of stable scientific consensus resulting from the rapid pace of technological change, but emerging frontier AI safety…

Artificial intelligence (AI) represents a technological upheaval with the potential to change human society. Because of its transformative potential, AI is increasingly becoming subject to regulatory initiatives at the global level. Yet, so…

We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Artificial Intelligence (AI) and Machine Learning (ML). A key…

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…

AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…

As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated…