# Antagonistic AI

arXiv: https://arxiv.org/abs/2402.07350 · HTML: https://mlsanity.com/paper/2402.07350/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 93 references that are in the map.
- First posted on arXiv 12 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://mlsanity.com/paper/2305.13160/) (2023)
- [When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour](https://mlsanity.com/paper/2311.09410/) (2023)
- [Machine Culture](https://mlsanity.com/paper/2311.11388/) (2023)
- [Benefits and Harms of Large Language Models in Digital Mental Health](https://mlsanity.com/paper/2311.14693/) (2023)
- [Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens](https://mlsanity.com/paper/2102.00593/) (2021)
- [A Human Rights-Based Approach to Responsible AI](https://mlsanity.com/paper/2210.02667/) (2022)
- [Generative Echo Chamber? Effects of LLM-Powered Search Systems on Diverse Information Seeking](https://mlsanity.com/paper/2402.05880/) (2024)

## Built on by (most cited first, 6 of 6)

- [Conversational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-making](https://mlsanity.com/paper/2503.14263/) (2025)
- [Privy: Envisioning and Mitigating Privacy Risks for Consumer-facing AI Product Concepts](https://mlsanity.com/paper/2509.23525/) (2025)
- [Social Simulations with Large Language Model Risk Utopian Illusion](https://mlsanity.com/paper/2510.21180/) (2025)
- [Reflections and New Directions for Human-Centered Large Language Models](https://mlsanity.com/paper/2605.06901/) (2026)
- [How Do Hackathons Foster Creativity? Towards AI Collaborative Evaluation of Creativity at Scale](https://mlsanity.com/paper/2503.04290/) (2025)
- [On the use of foundation models in cognitive science](https://mlsanity.com/paper/2608.07812/) (2026)

## 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.