Ingeborg Gabriel
Biographic Data
| ID | 1422988 |
|---|---|
| NAME | Ingeborg Gabriel |
| GIVEN NAMES | Ingeborg |
| FAMILY NAME | Gabriel |
| SIGNATURE | GABRIEL I |
| AFFILIATIONS | Google DeepMind (United Kingdom) |
| ORCID | 0000-0002-7552-4576 |
| VERIFIED | Yes |
| TOTAL WORKS | 12 |
| TOTAL CITATIONS | 9 |
| AUTHOR COUNT | 12 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2017 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 2 |
Why human–AI relationships need socioaffective alignment
Humans strive to design safe AI systems that align with our goals and remain under our control. However, as AI capabilities advance, we face a new challenge: the emergence of deeper, more persistent relationships between humans and AI systems. We explore how increasingly capable AI agents may generate the perception of deeper relationships with users, especially as AI becomes more personalised and agentic. This shift, from transactional interacti…
Manifestations of xenophobia in AI systems
Xenophobia is one of the key drivers of marginalisation, discrimination, and conflict, yet many prominent machine learning fairness frameworks fail to comprehensively measure or mitigate the resulting xenophobic harms. Here we aim to bridge this conceptual gap and help facilitate safe and ethical design of artificial intelligence (AI) solutions. We ground our analysis of the impact of xenophobia by first identifying distinct types of xenophobic h…
A matter of principle? AI alignment as the fair treatment of claims
The normative challenge of AI alignment centres upon what goals or values ought to be encoded in AI systems to govern their behaviour. A number of answers have been proposed, including the notion that AI must be aligned with human intentions or that it should aim to be helpful, honest and harmless. Nonetheless, both accounts suffer from critical weaknesses. On the one hand, they are incomplete: neither specification provides adequate guidance to …
The impact of advanced AI systems on democracy
Transformation of Religion: Interdisciplinary Perspectives
This volume presents different approaches to the concept of religion. Religion in modern societies is undergoing accelerated change. Traditional religious forms are dissolving and being overlaid with or replaced by new ones. This poses particular challenges for analyses of the current religious situation, which already presuppose an understanding of religion. But it is precisely this that is disputed in academic discourse about it. Against the ba…
In Conversation with Artificial Intelligence: Aligning language Models with Human Values
Large-scale language technologies are increasingly used in various forms of communication with humans across different contexts. One particular use case for these technologies is conversational agents, which output natural language text in response to prompts and queries. This mode of engagement raises a number of social and ethical questions. For example, what does it mean to align conversational agents with human norms or values? Which norms or…
Taxonomy of Risks posed by Language Models
Responsible innovation on large-scale Language Models (LMs) requires foresight into and in-depth understanding of the risks these models may pose. This paper develops a comprehensive taxonomy of ethical and social risks associated with LMs. We identify twenty-one risks, drawing on expertise and literature from computer science, linguistics, and the social sciences. We situate these risks in our taxonomy of six risk areas: I. Discrimination, Hate …
Toward a Theory of Justice for Artificial Intelligence
This essay explores the relationship between artificial intelligence and principles of distributive justice. Drawing upon the political philosophy of John Rawls, it holds that the basic structure of society should be understood as a composite of sociotechnical systems, and that the operation of these systems is increasingly shaped and influenced by AI. Consequently, egalitarian norms of justice apply to the technology when it is deployed in these…
Artificial Intelligence, Values, and Alignment
This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed pref…
Permissible Secrets
This article offers an account of the information condition on morally valid consent in the context of sexual relations. The account is grounded in rights. It holds that a person has a sufficient amount of information to give morally valid consent if, and only if, she has all the information to which she has a claim-right. A person has a claim-right to a piece of information if, and only if, a. it concerns a deal-breaker for her; b. it does not c…
Effective Altruism and its Critics
Effective altruism is a philosophy and a social movement that aims to revolutionise the way we do philanthropy. It encourages individuals to do as much good as possible, typically by contributing money to the best‐performing aid and development organisations. Surprisingly, this approach has met with considerable resistance among activists and aid providers who argue that effective altruism is insensitive to justice insofar as it overlooks the val…
The Problem with Yuppie Ethics
How much personal partiality do agent-centred prerogatives allow? If there are limits on what morality may demand of us, then how much does it permit? For a view Henry Shue has termed ‘yuppie ethics’, the answer to both questions is a great deal. It holds that rich people are morally permitted to spend large amounts of money on themselves, even when this means leaving those living in extreme poverty unaided. Against this view, I demonstrate that …
Toward a Theory of Justice for Artificial Intelligence
This essay explores the relationship between artificial intelligence and principles of distributive justice. Drawing upon the political philosophy of John Rawls, it holds that the basic structure of society should be understood as a composite of sociotechnical systems, and that the operation of these systems is increasingly shaped and influenced by AI. Consequently, egalitarian norms of justice apply to the technology when it is deployed in these…
Permissible Secrets
This article offers an account of the information condition on morally valid consent in the context of sexual relations. The account is grounded in rights. It holds that a person has a sufficient amount of information to give morally valid consent if, and only if, she has all the information to which she has a claim-right. A person has a claim-right to a piece of information if, and only if, a. it concerns a deal-breaker for her; b. it does not c…
A matter of principle? AI alignment as the fair treatment of claims
The normative challenge of AI alignment centres upon what goals or values ought to be encoded in AI systems to govern their behaviour. A number of answers have been proposed, including the notion that AI must be aligned with human intentions or that it should aim to be helpful, honest and harmless. Nonetheless, both accounts suffer from critical weaknesses. On the one hand, they are incomplete: neither specification provides adequate guidance to …
Effective Altruism and its Critics
Effective altruism is a philosophy and a social movement that aims to revolutionise the way we do philanthropy. It encourages individuals to do as much good as possible, typically by contributing money to the best‐performing aid and development organisations. Surprisingly, this approach has met with considerable resistance among activists and aid providers who argue that effective altruism is insensitive to justice insofar as it overlooks the val…
The Problem with Yuppie Ethics
How much personal partiality do agent-centred prerogatives allow? If there are limits on what morality may demand of us, then how much does it permit? For a view Henry Shue has termed ‘yuppie ethics’, the answer to both questions is a great deal. It holds that rich people are morally permitted to spend large amounts of money on themselves, even when this means leaving those living in extreme poverty unaided. Against this view, I demonstrate that …
Permissible Secrets
This article offers an account of the information condition on morally valid consent in the context of sexual relations. The account is grounded in rights. It holds that a person has a sufficient amount of information to give morally valid consent if, and only if, she has all the information to which she has a claim-right. A person has a claim-right to a piece of information if, and only if, a. it concerns a deal-breaker for her; b. it does not c…
Artificial Intelligence, Values, and Alignment
This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed pref…
Taxonomy of Risks posed by Language Models
Responsible innovation on large-scale Language Models (LMs) requires foresight into and in-depth understanding of the risks these models may pose. This paper develops a comprehensive taxonomy of ethical and social risks associated with LMs. We identify twenty-one risks, drawing on expertise and literature from computer science, linguistics, and the social sciences. We situate these risks in our taxonomy of six risk areas: I. Discrimination, Hate …
Toward a Theory of Justice for Artificial Intelligence
This essay explores the relationship between artificial intelligence and principles of distributive justice. Drawing upon the political philosophy of John Rawls, it holds that the basic structure of society should be understood as a composite of sociotechnical systems, and that the operation of these systems is increasingly shaped and influenced by AI. Consequently, egalitarian norms of justice apply to the technology when it is deployed in these…
Transformation of Religion: Interdisciplinary Perspectives
This volume presents different approaches to the concept of religion. Religion in modern societies is undergoing accelerated change. Traditional religious forms are dissolving and being overlaid with or replaced by new ones. This poses particular challenges for analyses of the current religious situation, which already presuppose an understanding of religion. But it is precisely this that is disputed in academic discourse about it. Against the ba…
In Conversation with Artificial Intelligence: Aligning language Models with Human Values
Large-scale language technologies are increasingly used in various forms of communication with humans across different contexts. One particular use case for these technologies is conversational agents, which output natural language text in response to prompts and queries. This mode of engagement raises a number of social and ethical questions. For example, what does it mean to align conversational agents with human norms or values? Which norms or…
Why human–AI relationships need socioaffective alignment
Humans strive to design safe AI systems that align with our goals and remain under our control. However, as AI capabilities advance, we face a new challenge: the emergence of deeper, more persistent relationships between humans and AI systems. We explore how increasingly capable AI agents may generate the perception of deeper relationships with users, especially as AI becomes more personalised and agentic. This shift, from transactional interacti…
Manifestations of xenophobia in AI systems
Xenophobia is one of the key drivers of marginalisation, discrimination, and conflict, yet many prominent machine learning fairness frameworks fail to comprehensively measure or mitigate the resulting xenophobic harms. Here we aim to bridge this conceptual gap and help facilitate safe and ethical design of artificial intelligence (AI) solutions. We ground our analysis of the impact of xenophobia by first identifying distinct types of xenophobic h…
A matter of principle? AI alignment as the fair treatment of claims
The normative challenge of AI alignment centres upon what goals or values ought to be encoded in AI systems to govern their behaviour. A number of answers have been proposed, including the notion that AI must be aligned with human intentions or that it should aim to be helpful, honest and harmless. Nonetheless, both accounts suffer from critical weaknesses. On the one hand, they are incomplete: neither specification provides adequate guidance to …
The impact of advanced AI systems on democracy
Ethics and Social Impacts of AI (8 works) · Philosophy (6 works) · Computer Science (5 works) · Epistemology (5 works) · Political science (5 works) · Psychology (5 works) · Sociology (5 works) · Law (4 works) · Law and economics (4 works) · Hate Speech and Cyberbullying Detection (3 works)