arXiv AI
Jul 28
Epistemic Norms for AI Safety and Alignment Research
arXiv:2607. 24243v1 Announce Type: new Abstract: Mainstream AI research emphasises capability growth and tolerates low failure rates when average-case performance is high.
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
arXiv:2607. 19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios.
Related stories
arXiv AI
Jul 2
From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems
arXiv:2410. 22526v2 Announce Type: replace Abstract: To effectively address potential harms from Artificial Intelligence (AI) systems, it is essential to identify and mitigate system-level hazards.
arXiv AI
1d ago
Position: AI Lock-In Is in Progress, and We Must Be Prepared
arXiv:2608. 14565v1 Announce Type: new Abstract: AI safety research has mainly focused on two areas: technical alignment (ensuring AI systems produce human-aligned outputs) and the regulation of generative AI's societal impacts (including unemployment risk and labor market disruption).
arXiv AI
6d ago
Agent Safety Should Be a Runtime Contract
arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
arXiv AI
2d ago
Why we need an AI-resilient society
arXiv:1912. 08786v3 Announce Type: replace-cross Abstract: Three generations of software have transformed the role of artificial intelligence in society.
arXiv AI
Jul 22
From Agent Failure Paths to Quantified Residual Risk: A Compositional Framework for Resilient Agentic AI
arXiv:2607. 18243v1 Announce Type: new Abstract: Agentic AI is crossing trust boundaries faster than current risk models can represent.
arXiv AI
Aug 11
Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents
arXiv:2608. 08601v1 Announce Type: new Abstract: To anticipate socio-technical risks from AI agents, organizations need taxonomies to classify them.
arXiv AI
Jul 17
Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AI
arXiv:2607. 14353v1 Announce Type: cross Abstract: As automated decision-making and data-driven technologies pervade society and are used to manage consequential outcomes, understanding the technology's capabilities, limitations, and attendant risks in context requires analysis of full sociotechnical systems.
arXiv AI
Jul 28
On AI Safety and Security Technical Debt in Engineering AI-Enabled Systems
arXiv:2607. 23365v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education.
arXiv AI
Jul 20
A Methodology for Auditable Trustworthiness Levels in AI Lifecycle Governance
arXiv:2607. 16130v1 Announce Type: cross Abstract: AI governance increasingly requires judgments about whether an AI system remains adequately trustworthy over time, whether observed changes are tolerable, and how such judgments should be documented in a transparent and contestable way.
arXiv AI
Jul 22
Operational Hallucination and Safety Drift in AI Agents
arXiv:2607. 18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.
arXiv AI
Aug 3
Beyond Component Testing: Validating Agentic AI Systems
arXiv:2607. 29405v1 Announce Type: new Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation.