arXiv:2608. 02660v1 Announce Type: cross Abstract: Advanced AI assistants engage users in extended interactions across a widening range of roles, including advice, decision support, collaboration, learning, emotional support, and companionship among others.
arXiv:2508. 09219v3 Announce Type: replace-cross Abstract: Recent advances in AI applications have raised growing concerns about the need for ethical guidelines and regulations to mitigate the risks posed by these technologies.
arXiv:2606. 13739v1 Announce Type: cross Abstract: This paper examines trade-offs between AI safety and well-being relative to (i) one of the most promising methods for finetuning super-capable AIs, 'Constitutional AI', and (ii) one of the most influential approaches to understanding complex ethical decision making and the conditions for the well-being of rational agents, 'Virtue Ethics'.
The paper examines how users handle harmful value conflicts with AI companions. By analyzing 146 posts and conducting a week-long study with 22 participants using the Minion technology probe, the authors find that users blend softer and harder strategies, especially when conflicts involve Universalism and Tradition values. The study highlights that such conflicts create asymmetric responsibility, with users shouldering unilateral repair work that AI companions cannot reciprocate, suggesting a need for platform-level safeguards.
The paper argues that AI alignment depends on a system’s ability to exhibit a coherent moral policy—stable, monotonic, decisive, and Pareto‑viable—rather than on any specific moral standard. The authors test nine large language models across varied moral scenarios and find that none maintain consistent verdicts, with surface‑form changes causing up to 99% shifts in outcomes. This indicates that current LLM agents lack the structural moral competence required for meaningful alignment.
The paper argues that AI should be evaluated not only by principles but by concrete protocols that translate commitments into roles, requirements, records, oversight, and assessment. It introduces a rupture test linking institutional baselines to system evaluation, and distinguishes evidence‑bounded deployment from measurement‑bounded governance. The authors propose the RISE AI architecture to make bounded, evidence‑based claims about Responsibility, Inclusivity, Safety, and Empowerment, emphasizing the need for engineering, institutional repair, and ongoing moral judgment.
The paper examines how the rise of AI capable of moral reasoning could reshape meta-ethics, traditionally focused on human ethics. It proposes a framework that identifies new questions about AI’s own ethics from both human and AI perspectives, dividing them into four domains. The author explores how existing meta-ethical theories might apply to these domains and argues that many human-centered formulations will need significant revision to accommodate AI.
arXiv:2609.38260v1 Announce Type: cross Abstract: Values such as honesty, autonomy, and confidentiality are often regarded as general principles underpinning AI alignment. However, what it means to a...
arXiv:2607. 20461v1 Announce Type: cross Abstract: Present implementations of artificial intelligence (AI) ethics do not adequately take feelings, or affect, into account.
arXiv:2606. 09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior.
arXiv:2606. 15485v1 Announce Type: cross Abstract: Agentic AI systems act autonomously, use tools, adapt to context, and operate in complex real-world environments.
arXiv:2609.36228v1 Announce Type: new Abstract: The EU AI Act introduces extensive compliance requirements for organizations that develop, deploy, or integrate AI systems. Many of these requirements...
arXiv:2607. 12755v1 Announce Type: cross Abstract: AI-enabled systems are seeing increasing deployment across numerous domains, with many being "black boxes" with respect to core functions and capabilities.