Get started
Author

Sören Mindermann

Inferring the effectiveness of government interventions against COVID-19
2020 · Jan M. Brauner, Sören Mindermann, et al. · Science · 1,064
Managing extreme AI risks amid rapid progress
2024 · Yoshua Bengio, Geoffrey Hinton, et al. · Science · 339
PDF
Understanding the effectiveness of government interventions against the resurgence of COVID-19 in Europe
2021 · Mrinank Sharma, Sören Mindermann, et al. · Nature Communications · 231
PDF
Mask wearing in community settings reduces SARS-CoV-2 transmission
2022 · Gavin Leech, Charlie Rogers-Smith, et al. · Proceedings of the National Academy of Sciences · 119
Changing composition of SARS-CoV-2 lineages and rise of Delta variant in England
2021 · Swapnil Mishra, Sören Mindermann, et al. · EClinicalMedicine · 114
Is the cure really worse than the disease? The health impacts of lockdowns during COVID-19
2021 · Gideon Meyerowitz-Katz, Samir Bhatt, et al. · BMJ Global Health · 106
PDF
Effectiveness assessment of non-pharmaceutical interventions: lessons learned from the COVID-19 pandemic
2023 · Adrian Lison, Nicolas Banholzer, et al. · The Lancet Public Health · 71
Seasonal variation in SARS-CoV-2 transmission in temperate climates: A Bayesian modelling study in 143 European regions
2022 · Tomáš Gavenčiak, Joshua Teperowski Monrad, et al. · PLoS Computational Biology · 63
PDF
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
2024 · Hubinger, Evan, Denison, Carson, et al. · arXiv (Cornell University) · 38
PDF
Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models
2020 · Jesson, Andrew, Mindermann, Sören, et al. · arXiv (Cornell University) · 37
PDF
Occam's razor is insufficient to infer the preferences of irrational agents
2017 · Armstrong, Stuart, Mindermann, Sören · arXiv (Cornell University) · 31
PDF
Alignment faking in large language models
2024 · Greenblatt, Ryan, Denison, Carson, et al. · arXiv (Cornell University) · 28
PDF
Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
2022 · Mindermann, Sören, Brauner, Jan, et al. · arXiv (Cornell University) · 18
PDF
How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
2020 · Sharma, Mrinank, Mindermann, Sören, et al. · arXiv (Cornell University) · 16
PDF
International AI Safety Report
2025 · Bengio, Yoshua, Mindermann, Sören, et al. · arXiv (Cornell University) · 15
PDF
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
2025 · Yoshua Bengio, Michael Cohen, et al. · SuperIntelligence - Robotics - Safety & Alignment · 14
PDF
A dataset of non-pharmaceutical interventions on SARS-CoV-2 in Europe
2022 · George Altman, Janvi Ahuja, et al. · Scientific Data · 11
PDF
Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
2021 · Jesson, Andrew, Mindermann, Sören, et al. · arXiv (Cornell University) · 11
PDF
Agentic Misalignment: How LLMs Could Be Insider Threats
2025 · Lynch, Aengus, Wright, Benjamin, et al. · arXiv (Cornell University) · 10
PDF
Language models transmit behavioural traits through hidden signals in data
2026 · Alex Cloud, Minh Le, et al. · Nature · 9
PDF
Impossibility of deducing preferences and rationality from human policy.
2017 · Stuart Armstrong, Sören Mindermann · arXiv (Cornell University) · 9
International Scientific Report on the Safety of Advanced AI (Interim Report)
2024 · Bengio, Yoshua, Mindermann, Sören, et al. · arXiv (Cornell University) · 7
PDF
Specific versus General Principles for Constitutional AI
2023 · Kundu, Sandipan, Bai, Yuntao, et al. · arXiv (Cornell University) · 7
PDF
The Singapore Consensus on Global AI Safety Research Priorities
2025 · Yoshua Bengio, Max Tegmark, et al. · SuperIntelligence - Robotics - Safety & Alignment · 5
PDF
Active Inverse Reward Design
2018 · Mindermann, Sören, Shah, Rohin, et al. · arXiv (Cornell University) · 5
PDF
Works count: 55
Citation count: 2,402
H-index: 15
I10-index: 19
Year
Topic
Type