mlsanityData to 7 Oct 2026

Antagonistic AI

arXiv 2402.07350 ↗First posted 12 Feb 2024cs.AI cs.HCcited by 5

Not on the map. Why?

Abstract (arXiv)

The vast majority of discourse around AI development assumes that subservient, "moral" models aligned with "human values" are universally beneficial -- in short, that good AI is sycophantic AI. We explore the shadow of the sycophantic paradigm, a design space we term antagonistic AI: AI systems that are disagreeable, rude, interrupting, confrontational, challenging, etc. -- embedding opposite behaviors or values. Far from being "bad" or "immoral," we consider whether antagonistic AI systems may sometimes have benefits to users, such as forcing users to confront their assumptions, build resilience, or develop healthier relational boundaries. Drawing from formative explorations and a speculative design workshop where participants designed fictional AI technologies that employ antagonism, we lay out a design space for antagonistic AI, articulating potential benefits, design techniques, and methods of embedding antagonistic elements into user experience. Finally, we discuss the many ethical challenges of this space and identify three dimensions for the responsible design of antagonistic AI -- consent, context, and framing.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 17 of its 93 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

17 of 93 references.

References · 17

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  2. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  3. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  4. 2023Whose Opinions Do Language Models Reflect?cited by 759
  5. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  6. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  7. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 533
  8. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
  9. 2023Cultural Bias and Cultural Alignment of Large Language Modelscited by 149
  10. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 94
  11. 2023Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debatecited by 92
  12. 2023When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviourcited by 61
5 more
  1. 2023Machine Culturecited by 55
  2. 2023Benefits and Harms of Large Language Models in Digital Mental Healthcited by 39
  3. 2021Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lenscited by 35
  4. 2022A Human Rights-Based Approach to Responsible AIcited by 20
  5. 2024Generative Echo Chamber? Effects of LLM-Powered Search Systems on Diverse Information Seekingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Conversational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-makingcited by 4
  2. 2025Privy: Envisioning and Mitigating Privacy Risks for Consumer-facing AI Product Conceptscited by 4
  3. 2025Social Simulations with Large Language Model Risk Utopian Illusioncited by 2
  4. 2025How Do Hackathons Foster Creativity? Towards AI Collaborative Evaluation of Creativity at Scalecited by 0
  5. 2026On the use of foundation models in cognitive sciencecited by 0