Related papers: Disentangling AI Alignment: A Structured Taxonomy …
Artificial intelligence (AI) systems are being readily and rapidly adopted, increasingly permeating critical domains: from consumer platforms and enterprise software to networked systems with embedded agents. While this has unlocked…
The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act…
The relationship between humans and artificial intelligence is no longer science fiction -- it's a growing reality reshaping how we live and work. AI has moved beyond research labs into everyday life, powering customer service chats,…
In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion remains largely…
Autonomous systems with cognitive features are on their way into the market. Within complex environments, they promise to implement complex and goal oriented behavior even in a safety related context. This behavior is based on a certain…
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,…
It is widely acknowledged that we need to establish where responsibility lies for the outputs and impacts of AI-enabled systems. This is important to achieve justice and compensation for victims of AI harms, and to inform policy and…
Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance they need. Decades of behavioral research, however, show that people often engage with AI…
As Artificial Intelligence (AI) systems increasingly assume consequential decision-making roles, a widening gap has emerged between technical capabilities and institutional accountability. Ethical guidance alone is insufficient to counter…
AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…
Artificial Intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives…
As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the most natural abstractions for predicting behaviour attribute…
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…
In real-world collaboration, alignment, process structure, and outcome quality do not exhibit a simple linear or one-to-one correspondence: similar alignment may accompany either rapid convergence or extensive multi-branch exploration, and…
It's widely expected that humanity will someday create AI systems vastly more intelligent than us, leading to the unsolved alignment problem of "how to control superintelligence." However, this commonly expressed problem is not only…
The proliferation of Artificial Intelligence (AI) has sparked an overwhelming number of AI ethics guidelines, boards and codes of conduct. These outputs primarily analyse competing theories, principles and values for AI development and…
As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This…
As artificial intelligence (AI) technologies continue to advance, effective risk assessment, regulation, and oversight are necessary to ensure that AI development and deployment align with ethical principles while preserving innovation and…
The concept of rationality is central to the field of artificial intelligence (AI). Whether we are seeking to simulate human reasoning, or trying to achieve bounded optimality, our goal is generally to make artificial agents as rational as…
Experiential AI is presented as a research agenda in which scientists and artists come together to investigate the entanglements between humans and machines, and an approach to human-machine learning and development where knowledge is…