EUVIMED · CrossrefJournal
SuperIntelligence - Robotics - Safety & Alignment
ISSN 3067-2627 · Carlson Research LLC
Latest articles
Geoffrey Hinton: Is AI Like Us and Will It Like Us?
Hinton: “Is AI Like Us and Will It Like Us?”
Highlights of the Issue
Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey
Explanations of the Fermi Paradox and the Drake Equation
HYDRA: A Hybrid Heuristic-Guided Deep Representation Architecture for Predicting Latent Zero-Day Vulnerabilities in Patched Functions
The 2025 Foundation Model Transparency Index
International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management
The Illusion of Thinking
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
Critical Review: Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
Deliberative Alignment: Reasoning Enables Safer Language Models
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
The First International AI Safety Report
Review: Large Language Models Pass the Turing Test
The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment
Humanity's Last Exam
Anthropic: Responsible Scaling Policy
AI Risk Categorization Decoded (AIR 2024)
Benchmark Early and Red Team Often
On Yampolskiy, Against Purposeful Artificial Intelligence Failures
Language-Guided World Models: A Model-Based Approach to AI Control
AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies
Models That Prove Their Own Correctness
The AI Risk Repository
Acceptable Use Policies for Foundation Models
Soft Nationalization: How the US Government Will Control AI Labs
Progress in Superhuman Theorem Proving?
EUVIMED