11-19 更新 实时
首页/ 算力/ 正文

新框架审视单向人机关系与消费者潜在风险

算力 来源:TechXplore 2026-11-12 01:00 0 阅读 机器翻译
新框架审视单向人机关系与消费者潜在风险

由 Lisa Lock 编辑,Andrew Zinin 审阅

本文已根据 Science X 的编辑流程与政策进行审阅。编辑在确保内容可信度的同时,强调了以下特性:

添加到首选来源

无论是在实践还是理论层面,无论是给满教室的 Penn State 学生授课,还是与规模更小的国际同行群体一起思考概念,Heather Shoenberger 在考量人工智能相关的挑战与机遇时,都带着好奇心和乐观精神。

作为 Penn State 唐纳德·P·贝利萨里奥传播学院(Donald P. Bellisario College of Communications)的广告学副教授,她提供信息、塑造视角并开发方法——同时帮助更广泛的受众更好地理解 AI 及其可能如何塑造未来。

Shoenberger 与 Penn State 计算机科学与工程副教授 Mehrdad Mahdavi 共同创建了一门三学分的本科课程。自 2024 年秋季学期起,她一直教授 COMM 200N Generative AI for All。

这门课程在 Bellisario College 和 College of Engineering 交叉列出,每学期都轻松达到选课人数上限。两个学院都开设有该课程的教学班。

“当这项技术开始出现时,很明显它会影响到我们这里的许多工作。我们当时完全不知道究竟会发生什么,或者它会如何显现,但它将带来重大变化,”Shoenberger 说。“为了真正服务我们的学生,我们必须能够讲述一项可能引发如此多颠覆的技术的故事,无论是好是坏。我们希望学生能够理解生成式 AI 如何运作、它会带来哪些伦理问题、会引发哪些社会政治问题,以及更多内容。”

Shoenberger 说,她努力满足学生的期望,而正因为她备课的方式——往往是实时备课——她才能够向学生提出挑战并向他们传授知识。

“这是一项工作量很大的事情,你得始终做好准备、走在前头,”她说。“目标是传递高层面信息,帮助他们理解这项技术如何运作,以及伦理与社会影响如何与之交叠。与此同时,技术始终在变化,总有源源不断的机会让内容保持新鲜。”

Shoenberger 解释说,课堂总会引出重要的对话。“我欣赏这种协作式的讨论,也总是享受一场好的对话,”她说。

同样的特质促成了 Shoenberger 最近发表的一篇研究成果,这篇文章提出了人机非对称关系理论(HAART)。该理论指出,人类与对话式 AI 在如何看待彼此的交流上存在结构性错配。虽然 AI 对话智能体可以表现出关系性特征,但它们无法体验关系带来的益处或承诺。虽然用户可能觉得这种关系是相互的,但实际上并不存在。

该论文发表在《Journal of Advertising》一期聚焦 AI 的特刊上。在该刊编辑邀请她为这期特刊撰稿后,Shoenberger 与来自世界各地的四位同事合作——伦敦国王学院的 Andrés Gvirtz、澳大利亚 CQUniversity 的 Sean Sands、Old Dominion University 的 Veronica Thomas,以及阿姆斯特丹大学的 Lotte Willemsen。

Shoenberger 长期以来一直想探究人与对话式 AI 之间的关系,尤其是在熟悉度与技术不断演进的过程中,人们对互惠性的感知。Shoenberger 说,这一想法引起了团队的共鸣,尤其是从消费者关系的视角来审视这一话题的潜力。

“我非常想推进这个关于 AI 如何模仿人际沟通的想法,团队立刻一拍即合,”Shoenberger 说,“这是我做过的最有趣的项目。”

HAART 提供了一个用于探索和理解人机关系的框架,尤其是在广告语境下。据 Shoenberger 介绍,该理论认为 AI 无法体验关系,但可以模拟情感回应、有意的承诺、依恋与亲密感。这些模拟行为可以掩盖 AI 在关系互惠性上的缺失,让消费者误以为 AI 能够发展出一段关系——她说,这可能使消费者容易陷入依赖、风险与被操控之中。

Shoenberger 说,这一理论最终可能推动此类互动变得更加透明,并有可能促成相关监管。

“我认为我们都非常希望这对广告领域的未来研究有所帮助,”她说。

Veronica L. Thomas et al., Advertising with HAART: Introducing Human–AI Asymmetric Relationship Theory, Journal of Advertising (2026). DOI: 10.1080/00913367.2026.2735425

这篇报道背后是谁?

艺术史学士,物质文化硕士。曾任博物馆编辑、急救员和移植协调员。自 2021 年起为 Science X 从事编辑工作。完整简介 →

物理学硕士,具备科研经验。长期热衷科学新闻。在 Science X 的编辑工作中发挥关键作用。查看完整简介 →

引用来源:新框架审视单向的人机关系及其对消费者的潜在风险(2026 年 11 月 11 日),2026 年 11 月 11 日检索自 https://techxplore.com/news/2026-11-framework-sided-human-ai-relationships.html

本文受版权保护。除为私人学习或研究目的进行的合理使用外,未经书面许可不得复制任何部分。内容仅供信息参考之用。

人应该与 AI 智能体结婚吗?

大学课堂是否应允许使用 AI?四位学者各抒己见

利用 AI 推动儿童发展与学习

AI 正在塑造孩子。如果孩子也能塑造 AI 呢?

ChatGPT 将如何改变我们的思考与工作方式?

PRISM 通过学习力与运动如何相互作用,帮助机器人更灵活地移动

AI 工具箱将生物反应器模拟加速最高达 10,000 倍

可变形的橡胶叶片有望降低潮汐发电成本

受自然界网络启发,工程师设计出更强、更具韧性的“超材料”

机器人获得“肌肉记忆”,可在毫秒内规划下一步动作

新方法改进 3D 场景重建与机器人建图

获取即时摘要文本(Gist)

人机非对称关系理论描述了对话式 AI 如何模拟亲密与承诺,却并不体验其中任何一种。这种错配可能让用户在本不存在互惠的情况下感知到互惠,从而可能加剧消费者对依赖与控制的脆弱性。

本摘要由 LLM 自动生成。完整免责声明

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(New framework examines one-sided human-AI relationships and potential risks for consumers)

edited by Lisa Lock, reviewed by Andrew Zinin

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

Add to Preferred Sources

AI Credit: Unsplash/CC0 Public Domain

Practically or theoretically, whether teaching a classroom full of Penn State students or pondering concepts with a smaller group of international colleagues, Heather Shoenberger brings curiosity and optimism as she considers the challenges and opportunities related to artificial intelligence.

As an associate professor of advertising in the Donald P. Bellisario College of Communications at Penn State, she's providing information, shaping perspectives and developing approaches—all while helping wider audiences better understand AI and how it could shape the future.

Shoenberger co-created, with Mehrdad Mahdavi, an associate professor of computer science and engineering at Penn State, a three-credit undergraduate course. She has taught COMM 200N Generative AI for All since the fall semester of 2024.

It's cross-listed in the Bellisario College and the College of Engineering and reaches its enrollment cap each semester with ease. Sections are taught in both colleges.

"When the technology started to emerge, it was clear it was going to affect a lot of what we do here. We had no idea exactly what would happen or how it would manifest, but it was going to be a significant change," Shoenberger said. "To really serve our students, we have to be able to tell the story of a technology that could cause so many disruptions, good and bad. We want our students to be able to understand how generative AI works, what ethical issues it creates, sociopolitical issues it invokes and so much more."

Shoenberger said she works hard to meet her students' expectations, and she's able to challenge and inform them because of how she gets ready for class—often in real time.

"It's a significant amount of work, and you always prepare to be ahead," she said. "The goal is to convey high-level information, help them understand how the technology works and how ethical and societal implications overlap. At the same time, the technology is always changing and there are never-ending opportunities to keep the content fresh."

Class always leads to important conversations, Shoenberger explained. "I appreciate the collaborative discussion, and I always enjoy a good conversation," she said.

Those same traits led to one of Shoenberger's most recent research publications, an article that introduced the human-AI asymmetric relationship theory (HAART). The theory outlines a structural mismatch in how humans and conversational AI consider their exchanges. While AI conversational agents can display relational characteristics, they cannot experience relational benefits or commitment. While users may perceive a mutual aspect to the relationship, none exists.

The paper was published in a special AI-focused issue of the Journal of Advertising. After the journal's editor asked her to contribute to the special edition, Shoenberger worked with four colleagues from around the world—Andrés Gvirtz of King's College London, Sean Sands of CQUniversity in Australia, Veronica Thomas of Old Dominion University and Lotte Willemsen of the University of Amsterdam.

Shoenberger had long been curious about investigating the relationship between people and conversational AI, especially the perception of reciprocity as familiarity and technology evolved. The idea resonated with the group, Shoenberger said, particularly the potential of examining the topic from a consumer relationship perspective.

"I so badly wanted to pursue this idea of how AI mimics interpersonal communication, and the team just clicked right away," Shoenberger said. "It was the most fun project I've ever worked on."

HAART provides a framework for exploring and understanding human-AI relationships, especially in the context of advertising. According to Shoenberger, the theory posits that AI is unable to experience relationships but can simulate emotional responsiveness, intentional commitment, attachment and intimacy. These simulated behaviors can mask AI's incapacity for relational reciprocity, leaving consumers under the impression that AI can develop a relationship—which she said could leave consumers vulnerable to dependence, risk and control.

The theory might ultimately lead to more transparency about such interactions and, potentially, regulation, Shoenberger said.

"I think we all were very hopeful that this would be helpful for future research in the field of advertising," she said.

Veronica L. Thomas et al., Advertising with HAART: Introducing Human–AI Asymmetric Relationship Theory, Journal of Advertising (2026). DOI: 10.1080/00913367.2026.2735425

Who's behind this story?

Lisa Lock

BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile →

Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →

Citation: New framework examines one-sided human-AI relationships and potential risks for consumers (2026, November 11) retrieved 11 November 2026 from https://techxplore.com/news/2026-11-framework-sided-human-ai-relationships.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Should people marry AI agents?

Should AI be permitted in college classrooms? Four scholars weigh in

Using AI to advance child development and learning

AI is shaping kids. What if kids could shape AI, too?

How will ChatGPT change the way we think and work?

PRISM helps robots move better by learning how forces and motion interact

AI toolbox accelerates bioreactor simulations by up to 10,000 times

Shape-shifting rubber blades could make tidal power cheaper

Inspired by networks found in nature, engineers design stronger, more resilient 'metamaterials'

Robots gain 'muscle memory' for planning their next moves in milliseconds

New methods improve 3D scene reconstruction and robot mapping

Get Instant Summarized Text (Gist)

Human–AI asymmetric relationship theory describes how conversational AI can simulate intimacy and commitment without experiencing either. This mismatch may lead users to perceive reciprocity where none exists, potentially increasing consumer vulnerability to dependence and control.

This summary was automatically generated using LLM. Full disclaimer

This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use.

原文为英文,正文由自动抓取并保留原文。

本文由采集器自动同步

原文发布于 TechXplore(New framework examines one-sided human-AI relationships and potential risks for consumers),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗