ai-safety

Documents about ai-safety

• The Design Paradox: Why Conversational AI Safety Architecture Needs Longitudinal Monitoring#681831Zenodo (CERN)
• STATIC and AI Safety#17583PhilArchive
• AI for science with considerations for AI safety#237410UR Research
• Evaluating whether AI models would sabotage AI safety research#138968arXiv CS
• Levels of Self-Improvement in AI and their Implications for AI Safety#774043PhilArchive
• Improving Trust in Safety-Critical AI Systems: Explainable AI and Anomaly Detection Frameworks for human safety in Smart Industries#274754IRIS
• The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems#306943arXiv CS
• Deception-Enabling Cognitive Capabilities in AI Systems#376411OSF
• (AI Rights 2): AI Safety Through Economic Integration: Why Markets Outperform Control#92270PhilArchive
• Automating Inequality? AI, Women's Online Safety, and the Case for Proactive Governance#638192Zenodo (CERN)
• The Adaptation Dilemma: Cultural Fit Does Not Guarantee Safety in Mental-Health LLMs#976744PsyArXiv
• On AI Safety and Security Technical Debt in Engineering AI-Enabled Systems#405576arXiv CS
• Harmonizing AI Safety Thresholds#381770arXiv CS
• AI Rights for Human Safety#704618PhilArchive
• Understanding Misalignment in AI Agents#634949eScholarship
• When Human-in-the-Loop Fails: An Answerability Test for Deployed AI Systems#28982DataCite
• When Human-in-the-Loop Fails: An Answerability Test for Deployed AI Systems#28983DataCite
• AI identity and self-concern: A new theory for AI rights and safety#119206PhilArchive
• The Möbius Strip — Why AI welfare, AI safety, and human welfare are the same problem#691577PhilArchive
• Constraint Architecture of Physical AI Deployment: A Coupled Interaction Model#181272Zenodo (CERN)
• The Cosmological Premise of AI Civilization Safety#101247PhilArchive
• AI Safety: A Climb To Armageddon?#723468PhilArchive
• (AI Rights 1): Beyond Control: AI Rights as a Safety Framework for Sentient Artificial Intelligence#108635PhilArchive
• 201 - the logical invalidation of rational thought according to AI - and incredibles consequences for AI SAFETY#689943PhilArchive
• The Adaptation Dilemma: Cultural Fit Does Not Guarantee Safety during Mental-Health Interactions with LLMs#1001906PsyArXiv
• Industry Self-Flagging and the Insufficiency Critique of Alignment#304802IRIS
• Human Natural Structure (HNS): A Structural Operating System for Human Understanding in AI — Full Manuscript#31488DataCite
• Human Natural Structure (HNS): A Structural Operating System for Human Understanding in AI — Full Manuscript#31489DataCite
• Delusions by design? How everyday AIs might be fuelling psychosis (and what can be done about it)#486111PsyArXiv
• Generative AI in healthcare education: How AI literacy gaps could compromise learning and patient safety#724081PhilArchive
• AI Applications in Food Safety and Quality Control#88228PhilArchive
• Position: AI Safety Requires Effective Controllability#229554arXiv CS
• Adversarial Prompting Framework for AI Safety Assessment#370283arXiv CS
• Item Response Theory for AI Safety#429395arXiv CS
• AI Safety: Not Optional, Not Later#673600arXiv CS
• Why Safety-First AI Governance Risks Producing Unsafe Systems#692739PhilArchive
• A Generative AI-Based Construction Safety Assistant Using Retrieval-Augmented Generation#675156Digital Commons @ Michigan Tech
• Unified Cognitive Dynamics v3.0: A Non-Markovian Framework for Cognitive Safety in High-Resonance Conversational AI#142359Zenodo (CERN)
• Artificial intelligence (AI) psychosis: mechanisms, clinical risks and safety considerations in generative AI chatbots.#295170NCBI PubMed Central
• Functional Safety in Industrial Automation: Integrating Programmable Logic Controllers, Safety PLCs, AI/ML/DL, Control Theory, Safety Invariants, and Uncertainty Quantification#30177DataCite
• Functional Safety in Industrial Automation: Integrating Programmable Logic Controllers, Safety PLCs, AI/ML/DL, Control Theory, Safety Invariants, and Uncertainty Quantification#30178DataCite
• AI Coach: A Prototype of Artificially Intelligent Coach for Psychological Safety and Mental Wellbeing in Healthcare#196202OSF
• Water Efficient Suppression Material Fire Behaviour and AI Driven Safety in Future Fire Protection Research#635124HAL (France)
• Safety as Understanding: Interpretive Braking, Comprehension-Based Restraint, and the Limits of Compliance-Based AI Safety#714114PhilArchive
• From Optional Safety to Architectural Responsibility: AI Governance after Models#716492PhilArchive
• Global Solutions vs. Local Solutions for the AI Safety Problem#773979PhilArchive
• Acceleration AI Ethics, the Debate between Innovation and Safety, and Stability AI’s Diffusion versus OpenAI’s Dall-E#74458PhilArchive
• allenai/wildjailbreak#786974Hugging Face Datasets
• Unsafe at any AUC: Unlearned Lessons From Sociotechnical Disasters for Responsible AI#682882Calhoun
• Agentic Microphysics: A Manifesto for Generative AI Safety#19044arXiv CS