Sotabase

Career

· Safety Researcher, Anthropic2024–
· PhD in Computer Science, University of California, Berkeley2021–2025

Publications (151)

Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet
PLoS Medicine · 2018
653
cited
Economy
Survival: Global Politics and Strategy · 2018
454
cited
The Architecture of Government: Rethinking Political Decentralization
2009
369
cited
Failing Forward? The Euro Crisis and the Incomplete Nature of European Integration
2016
361
cited
Automatically Auditing Large Language Models via Discrete Optimization
International Conference on Machine Learning · 2023
215
cited
Capturing Failures of Large Language Models via Human Cognitive Biases
Neural Information Processing Systems · 2022
123
cited
Robust Encodings: A Framework for Combating Adversarial Typos
Annual Meeting of the Association for Computational Linguistics · 2020
115
cited
Towards a theory of disintegration
2018
95
cited
Output Legitimacy and the Global Financial Crisis: Perceptions Matter
2009
89
cited
The Oxford Handbook of the European Union
2012
87
cited
Feedback Loops With Language Models Drive In-Context Reward Hacking
International Conference on Machine Learning · 2024
59
cited
Populism in Europe
2007
56
cited
Merkel’s Folly
2010
51
cited
Joining Europe's monetary club : the challenges for smaller member states
1998
49
cited
Selective Classification Can Magnify Disparities Across Groups
International Conference on Learning Representations · 2020
49
cited
Economic Adjustment and Political Transformation in Small States
2008
45
cited
Mass-Producing Failures of Multimodal Systems with Language Models
Neural Information Processing Systems · 2023
43
cited
Public Opinion and Enlargement
2004
38
cited
Italy's Sovereign Debt Crisis
2012
37
cited
Liberalized capital markets, state autonomy, and European monetary union
2003
37
cited
Sotabase
Erik Jones | Researcher Profile | Sotabase | Sotabase