mlsanityData to 7 Oct 2026

The Ethics of Advanced AI Assistants

arXiv 2404.16244 ↗First posted 24 Apr 2024cs.CYcited by 103

Not on the map. Why?

Cited by 27 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper focuses on the opportunities and the ethical and societal risks posed by advanced AI assistants. We define advanced AI assistants as artificial agents with natural language interfaces, whose function is to plan and execute sequences of actions on behalf of a user, across one or more domains, in line with the user's expectations. The paper starts by considering the technology itself, providing an overview of AI assistants, their technical foundations and potential range of applications. It then explores questions around AI value alignment, well-being, safety and malicious uses. Extending the circle of inquiry further, we next consider the relationship between advanced AI assistants and individual users in more detail, exploring topics such as manipulation and persuasion, anthropomorphism, appropriate relationships, trust and privacy. With this analysis in place, we consider the deployment of advanced assistants at a societal scale, focusing on cooperation, equity and access, misinformation, economic impact, the environment and how best to evaluate advanced AI assistants. Finally, we conclude by providing a range of recommendations for researchers, developers, policymakers and public stakeholders.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 28; 2025: 47; 2026: 28.

103 papers.

Sort:

By area:

  1. 2024AI Agents That Mattercited by 199
  2. 2024AirGapAgent: Protecting Privacy-Conscious Conversational Agentscited by 90
  3. 2024Clio: Privacy-Preserving Insights into Real-World AI Usecited by 66
  4. 2025Authenticated Delegation and Authorized AI Agentscited by 63
  5. 2024LLMs achieve adult human performance on higher-order theory of mind taskscited by 59
  6. 2025Contextual Agent Security: A Policy for Every Purposecited by 55
  7. 2025Multi-Agent Systems Execute Arbitrary Malicious Codecited by 52
  8. 2024Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Editscited by 49
  9. 2025Why human-AI relationships need socioaffective alignmentcited by 47
  10. 2025Infrastructure for AI Agentscited by 40
  11. 2024Moral Alignment for LLM Agentscited by 39
  12. 2024Operationalizing Contextual Integrity in Privacy-Conscious Assistantscited by 36
38 more
  1. 2024CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Datacited by 34
  2. 2024AI Alignment with Changing and Influenceable Reward Functionscited by 33
  3. 2024Cultural Evolution of Cooperation among LLM Agentscited by 30
  4. 2024Taking AI Welfare Seriouslycited by 28
  5. 2026The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systemscited by 27
  6. 2024From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agentscited by 25
  7. 2024Can Editing LLMs Inject Harm?cited by 22
  8. 2024IDs for AI Systemscited by 18
  9. 2025Compromising Honesty and Harmlessness in Language Models via Deception Attackscited by 17
  10. 2025Virtual Agent Economiescited by 17
  11. 2024Can LLMs make trade-offs involving stipulated pain and pleasure states?cited by 16
  12. 2026Intelligent AI Delegationcited by 16
  13. 2025Evaluating the Goal-Directedness of Large Language Modelscited by 15
  14. 2024Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agentcited by 14
  15. 2025The AI Agent Indexcited by 14
  16. 2025A Taxonomy of Linguistic Expressions That Contribute To Anthropomorphism of Language Technologiescited by 14
  17. 2025Technological folie `a deux: Feedback Loops Between AI Chatbots and Mental Illnesscited by 14
  18. 2024The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligencecited by 13
  19. 2025Taxonomy of User Needs and Actionscited by 13
  20. 2024Jailbreaking as a Reward Misspecification Problemcited by 11
  21. 2024Challenges in Human-Agent Communicationcited by 11
  22. 2025Measuring AI agent autonomy: Towards a scalable approach with code inspectioncited by 10
  23. 2025HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistantscited by 10
  24. 2025The Singapore Consensus on Global AI Safety Research Prioritiescited by 9
  25. 2025AI Agents and the Lawcited by 9
  26. 2024Private Yet Social: How LLM Chatbots Support and Challenge Eating Disorder Recoverycited by 8
  27. 2025Societal Alignment Frameworks Can Improve LLM Alignmentcited by 8
  28. 2025Build Agent Advocates, Not Platform Agentscited by 8
  29. 2025Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancementcited by 8
  30. 2025Distributional AGI Safetycited by 8
  31. 2024"I Am the One and Only, Your Cyber BFF": Understanding the Impact of GenAI Requires Understanding the Impact of Anthropomorphic AIcited by 7
  32. 2024Measuring Goal-Directednesscited by 7
  33. 2025In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AIcited by 7
  34. 2025Principles for Responsible AI Consciousness Researchcited by 6
  35. 2025Harmful Traits of AI Companionscited by 6
  36. 2025Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Valuecited by 6
  37. 2025Humanlike AI Design Increases Anthropomorphism but Yields Divergent Outcomes on Engagement and Trust Globallycited by 6
  38. 2025Position: Stop Acting Like Language Model Agents Are Normal Agentscited by 5

50 most cited of 103 All 103 (JSON)