相关论文: Expected Utilitarianism
Generative AI enables automated, effective manipulation at scale. Despite the growing general ethical discussion around generative AI, the specific manipulation risks remain inadequately investigated. This article outlines essential…
If capable AI agents are generally incentivized to seek power in service of the objectives we specify for them, then these systems will pose enormous risks, in addition to enormous benefits. In fully observable environments, most reward…
Intention is an important and challenging concept in AI. It is important because it underlies many other concepts we care about, such as agency, manipulation, legal responsibility, and blame. However, ascribing intent to AI systems is…
Artificial intelligence is already being applied in and impacting many important sectors in society, including healthcare, finance, and policing. These applications will increase as AI capabilities continue to progress, which has the…
The promise of AI is huge. AI systems have already achieved good enough performance to be in our streets and in our homes. However, they can be brittle and unfair. For society to reap the benefits of AI systems, society needs to be able to…
AI systems increasingly assist human decision making by producing preliminary assessments of complex inputs. However, such AI-generated assessments can often be noisy or systematically biased, raising a central question: how should costly…
For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a hard task, inverse reinforcement learning (IRL) aims to develop methods that allow for…
As AI systems become increasingly sophisticated, questions about machine consciousness and its ethical implications have moved from fringe speculation to mainstream academic debate. Current ethical frameworks in this domain often implicitly…
Machine learning (ML) systems across many application areas are increasingly demonstrating performance that is beyond that of humans. In response to the proliferation of such models, the field of Explainable AI (XAI) has sought to develop…
Algorithmic Information Theory has inspired intractable constructions of general intelligence (AGI), and undiscovered tractable approximations are likely feasible. Reinforcement Learning (RL), the dominant paradigm by which an agent might…
Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…
This chapter discusses the ethics of generative AI. It provides a technical primer to show how generative AI affords experiencing technology as if it were human, and this affordance provides a fruitful focus for the philosophical ethics of…
The concept of "task" is at the core of artificial intelligence (AI): Tasks are used for training and evaluating AI systems, which are built in order to perform and automatize tasks we deem useful. In other fields of engineering theoretical…
There are obvious benefits to integrating generative AI (artificial intelligence) into language learning and teaching. Those include using AI as a language tutor, creating learning materials, or assessing learner output. However, due to how…
What is agency, and why does it matter? In this work, we draw from the political science and philosophy literature and give two competing visions of what it means to be an (ethical) agent. The first view, which we term mechanistic, is…
The widespread use of artificial intelligence (AI) in many domains has revealed numerous ethical issues from data and design to deployment. In response, countless broad principles and guidelines for ethical AI have been published, and…
AI models that predict the future behavior of a system (a.k.a. predictive AI models) are central to intelligent decision-making. However, decision-making using predictive AI models often results in suboptimal performance. This is primarily…
With the rise of large multi-modal AI models, fuelled by recent interest in large language models (LLMs), the notion of artificial general intelligence (AGI) went from being restricted to a fringe community, to dominate mainstream large AI…
Solutions relying on artificial intelligence are devised to predict data patterns and answer questions that are clearly defined, involve an enumerable set of solutions, clear rules, and inherently binary decision mechanisms. Yet, as they…
Current ethical debates on the use of artificial intelligence (AI) in health care treat AI as a product of technology in three ways: First, by assessing risks and potential benefits of currently developed AI-enabled products with ethical…