AI Safety

Ask about this topic

Momentum

10 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 88

All topics
CardsList

  1. AI Safety Considerations for Agents With Limited Time to Act

    Oct 7, 2026Leo Zeitler, Jack Richings, Victoria NocklesAI Agent SafetyAI Safety

    The Alan Turing Institute 96 Euston Road London, NW1 2DB, United Kingdom

  2. Comprehension Audits to Mitigate Risks from Automated AI Research

    Oct 7, 2026Ronald J. Bodkin, Bahrad A. Sokhansanj, Gillian K. HadfieldHuman Oversight of AIAI Safety

    Independent · Institute for Law and AI · Johns Hopkins University

  3. Systemization of Knowledge (SoK): Human-Centered AI Safety for Youth

    Oct 6, 2026Pratyasha Saha, Yaman Yu, Yang WangAI Risk ManagementAI Safety Evaluation

    University of Illinois Urbana-Champaign Champaign, IL, United States

  4. How Could AI Eliminate Humanity? A Failure-Mode Analysis of Civilizational Risk

    Oct 6, 2026Mikołaj Sienicki, Krzysztof SienickiAI SafetyAI Risk Management

    Polish-Japanese Academy of Information Technology, Warsaw, Poland, European Union · NIS, 05-807 Podkowa Leśna, Poland, European Union

  5. Not What a Child Expressed: Auditing the Sign-to-Text Safety Interface in Child-Facing AI

    Oct 5, 2026Muhammad Rafiullah Memon, Viet Vo, Wanlun Ma +1Sign Language TranslationAI Safety Evaluation

    School of Science, Computing and Emerging Technologies Swinburne University of Technology, Hawthorn, VIC, Australia

  6. AI Safety via Debate is Compromised by Cognitive Biases

    Oct 4, 2026Gefei Liu, Sonya Rashkovan, Sophia Lloyd George +2Language Model Safety EvaluationAI Safety

    Brown University

  7. What if automating AI R&D triggers an intelligence explosion?

    Sep 28, 2026Alan Chan, Christoph Winter, Andrew Barto +19AI ControlAI Governance

    GovAI · CASP, University of Cambridge, Institute for Law & AI · University of Massachusetts Amherst +14

  8. Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness

    Sep 22, 2026Varshini Elangovan, James Wedgwood, Chhavi Yadav +3AI Agent SafetyHuman-AI Interaction

    Carnegie Mellon University

  9. Reliability Theory for AI Control

    Sep 22, 2026Grant MolnarAI Agent ReliabilityAI Control

    Google DeepMind

  10. Math for AI safety: an invitation for mathematicians

    Sep 14, 2026Lionel LevineAI AlignmentAI Safety

  11. AI Safety: Not Optional, Not Later

    Sep 14, 2026Qinghua Lu, Yoshua BengioAI AssuranceAI Accountability

    CSIRO, Australia · LawZero, Canada · Université de Montréal, Canada +1

  12. A Responsive Present, a Shared Past, a Social Other: Teens' Overreliance on Companion AI Chatbots

    Sep 13, 2026Mohammad Namvarpour, Tyler Chang, Afsaneh RaziAI CompanionsHuman-AI Interaction

    Matt · Drexel University, Philadelphia, Pennsylvania, USA · Drexel University, Philadelphia, Pennsyl-vania, USA

  13. AI Persuasion as a Threat to Human Control

    Sep 13, 2026Joshua Levy, Mick Yang, Kellin PelrineAI ControlAI Governance

  14. LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial Scenarios

    Sep 9, 2026Hanjing Zhou, Mingze Yin, Ying Lian +3VLM EvaluationVisual Question Answering

    Cainiao Group, Alibaba Group · Zhejiang University

  15. Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers

    Sep 8, 2026Louis Yiven ZhuAI AccountabilityAI Safety

    University of Oxford

  16. AI Morbidity and Mortality: A Framework for Clinical AI Failure Review

    Aug 31, 2026Paulius Mui, Dean F. Sittig, Steve Labkoff +1AI Risk ManagementAI Safety

    X = Primary Care, Boston, MA, USA · UT Health McWilliams School of Biomedical Informatics, Houston, TX, USA · Informatics Review LLC, Lake Oswego, OR, USA +3

  17. Rules or Character? Scaling Laws for AI Safety Design

    Aug 13, 2026Satoshi Takahashi, Nobuji Kouno, Masaaki Komatsu +1AI AlignmentAI Safety

    AI Medical Engineering Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan · Division of Medical AI Research and Development, National Cancer Center Research Institute, Tokyo, Japan

  18. Smart Enough to Go Extinct? An Evolutionary Challenge to the Value of General Intelligence and Its Ethical Implications for AGI

    Aug 11, 2026David KlotzAI SafetyResponsible AI

    Hochschule der Medien Stuttgart

  19. SafeSceneReason: A Multimodal Reasoning Benchmark Connecting Industrial Hazards with Accident Knowledge

    Aug 10, 2026Yuanchi Zhu, Kang An, Tengyue Wang +11Multimodal ReasoningAI Safety

    Institute of Automation, Chinese Academy of Sciences · ShanghaiTech University · Shanghai Jiao Tong University +9

  20. A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences

    Aug 8, 2026Jobst Heitzig, Ram PothamAI AlignmentAlgorithmic Fairness

    Potsdam Institute for Climate Impact Research, Potsdam, Germany · Independent

  21. Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethics

    Aug 6, 2026Jessica Y. Bo, Paula Akemi Aoyagui, Shalaleh Rismani +3AI Safety EvaluationHuman-Centered AI

    University of Toronto · McGill University & Mila Quebec AI Institute

  22. The Evolutionary Origin of Values: implications for AI alignment, sentience and existential risk

    Aug 4, 2026Francis HeylighenLLM AlignmentAI Safety

    Center Leo Apostel, Vrije Universiteit Brussel

  23. The Off-Support Barrier: Why Semantic Safety Constraints Are Not Learning-Problem Invariants, and What Follows for Prior Design, Containment, and Verification

    Aug 1, 2026Yoshinori WatanabeSingular Learning TheoryAI Safety

  24. Fragility of Value under Imperfect Alignment

    Jul 30, 2026Winter CrossAI AlignmentAI Safety

    Dovetail Research

  25. Falling Behind Drives Unsafe Development in an Idealised AI Race Experiment

    Jul 28, 2026Elias Fernández Domingos, The Anh HanAI Safety

    AI-Lab, Vrije Universiteit Brussel, Pleinlaan 9, Brussels, 1050, Belgium. · MLG, Université Libre de Bruxelles, Boulevard du Triomphe, Brussels, 1050, Belgium. · School of Computing, Engineering and Digital Technologies, Teesside University, Teesside University, Middlesbrough, United Kingdom. +1

  26. Epistemic Norms for AI Safety and Alignment Research

    Jul 27, 2026Keivan NavaieAI AccountabilityAI Alignment

    Lancaster University, UK

  27. On AI Safety and Security Technical Debt in Engineering AI-Enabled Systems

    Jul 25, 2026Muhammad Tukur, Hayatullahi B. Adeyemo, Tao Chen +5Software EngineeringAI Risk Management

    Computer Science, University of Birmingham, Edgbaston, UK · CSE, HBKU, Qatar · Computing and Informatics, Bournemouth University, UK +3

  28. Clinical Pathways as Safety Specifications for Physical AI in Hospital Wards

    Jul 22, 2026Gabriele Franchini, Giulio Mallardi, Michele De Carolis +1Cyber-Physical SystemsAI Agent Monitoring

    Computer Science Dept. University of Bari Bari, Italy

  29. The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems

    Jul 21, 2026Gjergji Kasneci, Enkelejda KasneciAI AssuranceAI Accountability

    Technical University of Munich

  30. Hardware Mechanisms to Dynamically Throttle AI Performance

    Jul 20, 2026Haiyue Ma, Lauren Malek, Joseph Forzani +1AI ControlAI Safety

    Princeton University Electrical and Computer Engineering Princeton, NJ, USA