Jacqueline Harding
Biographic Data
| ID | 5086967 |
|---|---|
| NAME | Jacqueline Harding |
| GIVEN NAMES | Jacqueline |
| FAMILY NAME | Harding |
| SIGNATURE | HARDING J |
| AFFILIATIONS | Stanford University |
| ORCID | 0000-0002-2239-7817 |
| VERIFIED | Yes |
| TOTAL WORKS | 9 |
| TOTAL CITATIONS | 4 |
| AUTHOR COUNT | 9 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2012 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 1 |
A Communication‐First Account of Explanation
This paper develops a formal account of causal explanation, grounded in a theory of conversational pragmatics, and inspired by the interventionist idea that explanation is about asking and answering what‐if‐things‐had‐been‐different questions. We illustrate the fruitfulness of the account, relative to previous accounts, by showing that widely recognized “explanatory virtues” emerge naturally, as do subtle empirical patterns concerning the impact …
What is AI safety? What do we want it to be
The field of AI safety seeks to prevent or reduce the harms caused by AI systems. A simple and appealing account of what is distinctive of AI safety as a field holds that this feature is constitutive: a research project falls within the purview of AI safety just in case it aims to prevent or reduce the harms caused by AI systems. Call this appealingly simple account The Safety Conception of AI safety . Despite its simplicity and appeal, we argue …
AI language models cannot replace human research participants
What Is It for a Machine Learning Model to Have a Capability
What can contemporary machine learning (ML) models do? Given the proliferation of ML models in society, answering this question matters to a variety of stakeholders, both public and private. The evaluation of models' capabilities is rapidly emerging as a key subfield of modern ML, buoyed by regulatory attention and government grants. Despite this, the notion of an ML model possessing a capability has not been interrogated: what are we saying when…
Operationalising Representation in Natural Language Processing
Proxy selection in transitive proxy voting
Everettian Quantum Mechanics and the Metaphysics of Modality
This article sits at a point of intersection between the philosophy of physics and the metaphysics of modality. There are clear similarities between Everettian quantum mechanics and various modal metaphysical theories, but there have hitherto been few attempts at exploring how the two topics relate. In this article, I build on a series of recent papers by Wilson ([2011], [2012], [2013]), who argues that Everettian quantum mechanics’ connections w…
Cool Food Planet, a science-based educational website that engages children aged 6–12 years old in nutrition, food safety & physical activity
New instruments for communication
[No abstract available] The communication landscape is changing: Why do humans constantly desire new ways to communicate? Now that multi-modal texts are demanding that we rethink what it means to be literate it is important that we question how the reader/viewer’s expectations have evolved and how new instruments for communication are being embraced. There is a growing demand for bite-sized information: it appears that, as consumers of communicat…
Operationalising Representation in Natural Language Processing
Everettian Quantum Mechanics and the Metaphysics of Modality
This article sits at a point of intersection between the philosophy of physics and the metaphysics of modality. There are clear similarities between Everettian quantum mechanics and various modal metaphysical theories, but there have hitherto been few attempts at exploring how the two topics relate. In this article, I build on a series of recent papers by Wilson ([2011], [2012], [2013]), who argues that Everettian quantum mechanics’ connections w…
New instruments for communication
[No abstract available] The communication landscape is changing: Why do humans constantly desire new ways to communicate? Now that multi-modal texts are demanding that we rethink what it means to be literate it is important that we question how the reader/viewer’s expectations have evolved and how new instruments for communication are being embraced. There is a growing demand for bite-sized information: it appears that, as consumers of communicat…
Cool Food Planet, a science-based educational website that engages children aged 6–12 years old in nutrition, food safety & physical activity
Everettian Quantum Mechanics and the Metaphysics of Modality
This article sits at a point of intersection between the philosophy of physics and the metaphysics of modality. There are clear similarities between Everettian quantum mechanics and various modal metaphysical theories, but there have hitherto been few attempts at exploring how the two topics relate. In this article, I build on a series of recent papers by Wilson ([2011], [2012], [2013]), who argues that Everettian quantum mechanics’ connections w…
Proxy selection in transitive proxy voting
Operationalising Representation in Natural Language Processing
AI language models cannot replace human research participants
What Is It for a Machine Learning Model to Have a Capability
What can contemporary machine learning (ML) models do? Given the proliferation of ML models in society, answering this question matters to a variety of stakeholders, both public and private. The evaluation of models' capabilities is rapidly emerging as a key subfield of modern ML, buoyed by regulatory attention and government grants. Despite this, the notion of an ML model possessing a capability has not been interrogated: what are we saying when…
What is AI safety? What do we want it to be
The field of AI safety seeks to prevent or reduce the harms caused by AI systems. A simple and appealing account of what is distinctive of AI safety as a field holds that this feature is constitutive: a research project falls within the purview of AI safety just in case it aims to prevent or reduce the harms caused by AI systems. Call this appealingly simple account The Safety Conception of AI safety . Despite its simplicity and appeal, we argue …
A Communication‐First Account of Explanation
This paper develops a formal account of causal explanation, grounded in a theory of conversational pragmatics, and inspired by the interventionist idea that explanation is about asking and answering what‐if‐things‐had‐been‐different questions. We illustrate the fruitfulness of the account, relative to previous accounts, by showing that widely recognized “explanatory virtues” emerge naturally, as do subtle empirical patterns concerning the impact …
Computer Science (7 works) · Epistemology (3 works) · Philosophy (3 works) · World Wide Web (3 works) · Artificial Intelligence (2 works) · Artificial Intelligence (2 works) · Cognitive Science and Education Research (2 works) · Epistemology, Ethics, and Metaphysics (2 works) · Explainable Artificial Intelligence (XAI (2 works) · Human–computer interaction (2 works)