{"total":27,"rows":[{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2306.06924","title":"TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI","created":"2023-06-12","cited_by_count":26,"area":null},{"id":"2403.04471","title":"The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists","created":"2024-03-07","cited_by_count":22,"area":null},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"area":null},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2103.12142","title":"Combining Reward Information from Multiple Sources","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2206.11812","title":"Formalizing the Problem of Side Effect Regularization","created":"2022-06-23","cited_by_count":3,"area":null},{"id":"2102.00834","title":"Counterfactual Planning in AGI Systems","created":"2021-01-29","cited_by_count":2,"area":null},{"id":"2503.04750","title":"AI Agents Should be Regulated Based on the Extent of Their Autonomous Operations","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2106.02617","title":"Be Considerate: Objectives, Side Effects, and Deciding How to Act","created":"2021-06-04","cited_by_count":1,"area":null},{"id":"2508.00159","title":"Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2511.04177","title":"When Assisting One Disempowers Another","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2101.12509","title":"Challenges for Using Impact Regularizers to Avoid Negative Side Effects","created":"2021-01-29","cited_by_count":0,"area":null},{"id":"2112.10190","title":"Demanding and Designing Aligned Cognitive Architectures","created":"2021-12-19","cited_by_count":0,"area":null},{"id":"2208.04273","title":"Improving performance in multi-objective decision-making in Bottles environments with soft maximin approaches","created":"2022-08-08","cited_by_count":0,"area":null},{"id":"2303.03139","title":"Low impact agency: review and discussion","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2304.03081","title":"Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2311.04240","title":"Environmental-Impact Based Multi-Agent Reinforcement Learning","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2510.04901","title":"Focused Skill Discovery: Learning to Control Specific State Variables while Minimizing Side Effects","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2510.15395","title":"Corrigibility Transformation: Constructing Goals That Accept Updates","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.15282","title":"Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2603.07315","title":"Shutdown Safety Valves for Advanced AI","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2608.08240","title":"A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.12372","title":"Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.04444","title":"HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.34840","title":"Nociception as a Control Primitive: Afferent Channels and Nociceptive Memory for Agents Deployed in One Body","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}