3.1k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of OxfordGB5 papers
- Goethe University FrankfurtDE4 papers
- Institute on GovernanceCA3 papers
- Mila - Quebec Artificial Intelligence InstituteCA2 papers
- Princeton UniversityUS2 papers
- University of CambridgeGB2 papers
- University of TorontoCA2 papers
- Center for Information TechnologyUS1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- Epoch Biosciences (United States)US1 paper
- German Cancer Research CenterDE1 paper
- Harvard University PressUS1 paper
13 papers
On Regulating Downstream AI Developers
Sophie Williams, Jonas Schuett, Markus Anderljung
Foundation models - models trained on broad data that can be adapted to a wide range of downstream tasks - can pose significant risks, ranging from intimate image abuse, cyberattac…
From Principles to Rules: A Regulatory Approach for Frontier AI
Jonas Schuett, Markus Anderljung, Alexis Carlier +2
Several jurisdictions are starting to regulate frontier artificial intelligence (AI) systems, i.e. general-purpose AI systems that match or exceed the capabilities present in the m…
Black-Box Access is Insufficient for Rigorous AI Audits
Stephen Casper, Carson Ezell, Charlotte Siegmann +18
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of access granted to a…
Frontier AI developers need an internal audit function
Jonas Schuett
This article argues that frontier artificial intelligence (AI) developers need an internal audit function. First, it describes the role of internal audit in corporate governance: i…
Auditing large language models: a three-layered approach
Jakob Mökander, Jonas Schuett, Hannah Rose Kirk +1
Large language models (LLMs) represent a major advance in artificial intelligence (AI) research. However, the widespread use of LLMs is also coupled with significant ethical and so…
Three lines of defense against risks from AI
Jonas Schuett
Organizations that develop and deploy artificial intelligence (AI) systems need to manage the associated risks - for economic, legal, and ethical reasons. However, it is not always…
Risk management in the Artificial Intelligence Act
Jonas Schuett
The proposed EU AI Act is the first comprehensive attempt to regulate AI in a major jurisdiction. This article analyses Article 9, the key risk management provision in the AI Act.…
Compute Trends Across Three Eras of Machine Learning
Jaime Sevilla, Lennart Heim, Anson Ho +3
Compute, data, and algorithmic advances are the three fundamental factors that guide the progress of modern Machine Learning (ML). In this paper we study trends in the most readily…
Filling gaps in trustworthy development of AI
Shahar Avin, Haydn Belfield, Miles Brundage +9
The range of application of artificial intelligence (AI) is vast, as is the potential for harm. Growing awareness of potential risks from AI systems has spurred action to address t…
The Future of Digital Health with Federated Learning
Nicola Rieke, Jonny Hancox, Wenqi Li +14
Data-driven Machine Learning has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern…
The Logic of Strategic Assets: From Oil to Artificial Intelligence
Jeffrey Ding, Allan Dafoe
What resources and technologies are strategic? This question is often the focus of policy and theoretical debates, where the label "strategic" designates those assets that warrant…
Defining the scope of AI regulations
Jonas Schuett
The paper argues that the material scope of AI regulations should not rely on the term "artificial intelligence (AI)". The argument is developed by proposing a number of requiremen…
The magnitude and direction of collider bias for binary variables
Trang Quynh Nguyen, Allan Dafoe, Elizabeth L. Ogburn
Suppose we are interested in the effect of variable on variable . If and both influence, or are associated with variables that influence, a common outcome, called a…