Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety

• URL: http://arxiv.org/abs/2305.19223v1
• Date: Tue, 30 May 2023 17:14:01 GMT
• Title: Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety
• Authors: Catalin Mitelut, Ben Smith, Peter Vamplew
• Abstract summary: We argue that alignment to human intent is insufficient for safe AI systems. We argue that preservation of long-term agency of humans may be a more robust standard.
• Score: 2.3572498744567127
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs and AGIs will harm humans via intentional misuse (AI-misuse) or through accidents (AI-accidents). In respect of AI-accidents, there is an increasing effort focused on developing algorithms and paradigms that ensure AI systems are aligned to what humans intend, e.g. AI systems that yield actions or recommendations that humans might judge as consistent with their intentions and goals. Here we argue that alignment to human intent is insufficient for safe AI systems and that preservation of long-term agency of humans may be a more robust standard, and one that needs to be separated explicitly and a priori during optimization. We argue that AI systems can reshape human intention and discuss the lack of biological and psychological mechanisms that protect humans from loss of agency. We provide the first formal definition of agency-preserving AI-human interactions which focuses on forward-looking agency evaluations and argue that AI systems - not humans - must be increasingly tasked with making these evaluations. We show how agency loss can occur in simple environments containing embedded agents that use temporal-difference learning to make action recommendations. Finally, we propose a new area of research called "agency foundations" and pose four initial topics designed to improve our understanding of agency in AI-human interactions: benevolent game theory, algorithmic foundations of human rights, mechanistic interpretability of agency representation in neural-networks and reinforcement learning from internal states.

Related papers

• Position Paper: Agent AI Towards a Holistic Intelligence [53.35971598180146]
  We emphasize developing Agent AI -- an embodied system that integrates large foundation models into agent actions. In this paper, we propose a novel large action model to achieve embodied intelligent behavior, the Agent Foundation Model.
  arXiv  Detail & Related papers  (2024-02-28T16:09:56Z)
• Managing extreme AI risks amid rapid progress [171.05448842016125]
  We describe risks that include large-scale social harms, malicious uses, and irreversible loss of human control over autonomous AI systems. There is a lack of consensus about how exactly such risks arise, and how to manage them. Present governance initiatives lack the mechanisms and institutions to prevent misuse and recklessness, and barely address autonomous systems.
  arXiv  Detail & Related papers  (2023-10-26T17:59:06Z)
• Reflective Hybrid Intelligence for Meaningful Human Control in Decision-Support Systems [4.1454448964078585]
  We introduce the notion of self-reflective AI systems for meaningful human control over AI systems. We propose a framework that integrates knowledge from psychology and philosophy with formal reasoning methods and machine learning approaches. We argue that self-reflective AI systems can lead to self-reflective hybrid systems (human + AI)
  arXiv  Detail & Related papers  (2023-07-12T13:32:24Z)
• Applying HCAI in developing effective human-AI teaming: A perspective from human-AI joint cognitive systems [10.746728034149989]
  Research and application have used human-AI teaming (HAT) as a new paradigm to develop AI systems. We elaborate on our proposed conceptual framework of human-AI joint cognitive systems (HAIJCS) We propose a conceptual framework of human-AI joint cognitive systems (HAIJCS) to represent and implement HAT.
  arXiv  Detail & Related papers  (2023-07-08T06:26:38Z)
• Fairness in AI and Its Long-Term Implications on Society [68.8204255655161]
  We take a closer look at AI fairness and analyze how lack of AI fairness can lead to deepening of biases over time. We discuss how biased models can lead to more negative real-world outcomes for certain groups. If the issues persist, they could be reinforced by interactions with other risks and have severe implications on society in the form of social unrest.
  arXiv  Detail & Related papers  (2023-04-16T11:22:59Z)
• BIASeD: Bringing Irrationality into Automated System Design [12.754146668390828]
  We claim that the future of human-machine collaboration will entail the development of AI systems that model, understand and possibly replicate human cognitive biases. We categorize existing cognitive biases from the perspective of AI systems, identify three broad areas of interest and outline research directions for the design of AI systems that have a better understanding of our own biases.
  arXiv  Detail & Related papers  (2022-10-01T02:52:38Z)
• Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
  Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
  arXiv  Detail & Related papers  (2022-01-26T18:53:09Z)
• On some Foundational Aspects of Human-Centered Artificial Intelligence [52.03866242565846]
  There is no clear definition of what is meant by Human Centered Artificial Intelligence. This paper introduces the term HCAI agent to refer to any physical or software computational agent equipped with AI components. We see the notion of HCAI agent, together with its components and functions, as a way to bridge the technical and non-technical discussions on human-centered AI.
  arXiv  Detail & Related papers  (2021-12-29T09:58:59Z)
• Meaningful human control over AI systems: beyond talking the talk [8.351027101823705]
  We identify four properties which AI-based systems must have to be under meaningful human control. First, a system in which humans and AI algorithms interact should have an explicitly defined domain of morally loaded situations. Second, humans and AI agents within the system should have appropriate and mutually compatible representations. Third, responsibility attributed to a human should be commensurate with that human's ability and authority to control the system.
  arXiv  Detail & Related papers  (2021-11-25T11:05:37Z)
• Trustworthy AI: A Computational Perspective [54.80482955088197]
  We focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Non-discrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability & Auditability, and (vi) Environmental Well-Being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems.
  arXiv  Detail & Related papers  (2021-07-12T14:21:46Z)
• Socially Responsible AI Algorithms: Issues, Purposes, and Challenges [31.382000425295885]
  Technologists and AI researchers have a responsibility to develop trustworthy AI systems. To build long-lasting trust between AI and human beings, we argue that the key is to think beyond algorithmic fairness.
  arXiv  Detail & Related papers  (2021-01-01T17:34:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.