{"total":22,"rows":[{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80,"area":null},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2210.10765","title":"When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning","created":"2022-10-19","cited_by_count":21,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2103.12142","title":"Combining Reward Information from Multiple Sources","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2206.11812","title":"Formalizing the Problem of Side Effect Regularization","created":"2022-06-23","cited_by_count":3,"area":null},{"id":"2410.00258","title":"Possible Principles for Aligned Structure Learning Agents","created":"2024-09-30","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":"2501.15446","title":"NP-Hard Lower Bound Complexity for Semantic Self-Verification","created":"2025-01-26","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":"2111.14324","title":"Is the Rush to Machine Learning Jeopardizing Safety? Results of a Survey","created":"2021-11-29","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":"2311.12004","title":"Risk-averse Batch Active Inverse Reward Design","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2504.16622","title":"Cognitive Silicon: An Architectural Blueprint for Post-Industrial Computing Systems","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2608.14795","title":"Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous","created":"2026-08-14","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}],"next_cursor":null}