5 papers
Mechanistic Interpretability Needs Philosophy
Iwan Williams, Ninell Oldenburg, Ruchira Dhar +6
Mechanistic interpretability (MI) aims to explain how neural networks work by uncovering their underlying mechanisms. As the field grows in influence, it is increasingly important…
Update Opacity: Epistemic Accessibility and Governance Under AI System Change
Andrea Ferrario, Joshua Hatherley
Machine learning models embedded in deployed AI systems are routinely updated to maintain correct functioning over time. Yet such updates can generate update opacity: users may not…
Postmortem avatars in grief therapy: Prospects, ethics, and governance
Joshua Hatherley, Sandrine R. Schiller, Iwan Williams +3
Postmortem avatars (PMAs) -- AI systems that simulate a deceased person by being fine-tuned on data they generated or that was generated about them -- have attracted growing schola…
Federated learning, ethics, and the double black box problem in medical AI
Joshua Hatherley, Anders Søgaard, Angela Ballantyne +1
Federated learning (FL) is a machine learning approach that allows multiple devices or institutions to collaboratively train a model without sharing their local data with a third-p…
Data over dialogue: Why artificial intelligence is unlikely to humanise medicine
Joshua Hatherley
Recently, a growing number of experts in artificial intelligence (AI) and medicine have be-gun to suggest that the use of AI systems, particularly machine learning (ML) systems, is…