{"total":16,"rows":[{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2412.12140","title":"Frontier AI systems have surpassed the self-replicating red line","created":"2024-12-09","cited_by_count":17,"area":null},{"id":"2508.14927","title":"AI Testing Should Account for Sophisticated Strategic Behaviour","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2503.17378","title":"Large language model-powered AI systems achieve self-replication with no human intervention","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2506.03755","title":"Misalignment or misuse? The AGI alignment tradeoff","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2601.00360","title":"Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems","created":"2026-01-01","cited_by_count":4,"area":null},{"id":"2507.07765","title":"Distributed and Decentralised Training: Technical Governance Challenges in a Shifting AI Landscape","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2407.00805","title":"Towards Shutdownable Agents via Stochastic Choice","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2505.02313","title":"What Is AI Safety? What Do We Want It to Be?","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2606.12420","title":"Eigenism: Ethics for a Human-AI Future","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2408.15116","title":"Evaluating Stability of Unreflective Alignment","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2510.08576","title":"Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2511.13725","title":"Can We Stop Malicious AI? KILLBENCH: A Benchmark for External AI Kill Switch Feasibility","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2601.09765","title":"AI Survival Stories: a Taxonomic Analysis of AI Existential Risk","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2606.05734","title":"When AI Says It Feels","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.08296","title":"Revisiting the shutdown problem","created":"2026-06-06","cited_by_count":0,"area":null}],"next_cursor":null}