Sören Mindermann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sören Mindermann has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Gavin Leech
Department of Computer Science, University of Bristol, UK
8 shared publications - Mrinank Sharma
University of Oxford
7 shared publications - Jan Markus Brauner
University of Oxford
6 shared publications - Jan Kulveit
Alignment of Complex Systems Research Group, Center for Theoretical Studies, Charles University
5 shared publications - Samir Bhatt
Section for Health Data Science and AI, Department of Public Health, University of Copenhagen, Copenhagen, Denmark
5 shared publications - Yarin Gal
University of Oxford
5 shared publications
Latest Publications
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 3148-3161
In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 3148-3161
Open AccessIn Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?
- Open Access
The Alignment Problem from a Deep Learning Perspective
In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities at many critical tasks. We argue that, without substantial effort to prevent it, AGIs could learn to pursue goals that are in conflict (i.e. misaligned) with human interests. If trained like today's most capable models, AGIs could learn to act deceptively to receive higher reward, learn misaligned internally-represented goals which generalize beyond their fine-tuning distributions, and pursue those goals using power-seeking strategies. We review emerging evidence for these properties. AGIs with these properties would be difficult to align and may appear aligned even when they are not. Finally, we briefly outline how the deployment of misaligned AGIs might irreversibly undermine human control over the world, and we review research directions aimed at preventing this outcome.
Open AccessThe Alignment Problem from a Deep Learning Perspective
In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities at many critical tasks. We argue that, without substantial effort to prevent it, AGIs could learn to pursue goals that are in conflict (i.e. misaligned) with human interests. If trained like today's most capable models, AGIs could learn to act deceptively to receive higher reward, learn misaligned internally-represented goals which generalize beyond their fine-tuning distributions, and pursue those goals using power-seeking strategies. We review emerging evidence for these properties. AGIs with these properties would be difficult to align and may appear aligned even when they are not. Finally, we briefly outline how the deployment of misaligned AGIs might irreversibly undermine human control over the world, and we review research directions aimed at preventing this outcome.
- Open Access
- 26 August 2022
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 18 (8) , e1010435
Seasonal variation in SARS-CoV-2 transmission in temperate climates: A Bayesian modelling study in 143 European regions
Although seasonal variation has a known influence on the transmission of several respiratory viral infections, its role in SARS-CoV-2 transmission remains unclear. While there is a sizable and growing literature on environmental drivers of COVID-19 transmission, recent reviews have highlighted conflicting and inconclusive findings. This indeterminacy partly owes to the fact that seasonal variation relates to viral transmission by a complicated web of causal pathways, including many interacting biological and behavioural factors. Since analyses of specific factors cannot determine the aggregate strength of seasonal forcing, we sidestep the challenge of disentangling various possible causal paths in favor of a holistic approach. We model seasonality as a sinusoidal variation in transmission and infer a single Bayesian estimate of the overall seasonal effect. By extending two state-of-the-art models of non-pharmaceutical intervention (NPI) effects and their datasets covering 143 regions in temperate Europe, we are able to adjust our estimates for the role of both NPIs and mobility patterns in reducing transmission. We find strong seasonal patterns, consistent with a reduction in the time-varying reproduction number R(t) (the expected number of new infections generated by an infectious individual at time t) of 42.1% (95% CI: 24.7%—53.4%) from the peak of winter to the peak of summer. These results imply that the seasonality of SARS-CoV-2 transmission is comparable in magnitude to the most effective individual NPIs but less than the combined effect of multiple interventions.
- 26 August 2022
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 18 (8) , e1010435
Open AccessSeasonal variation in SARS-CoV-2 transmission in temperate climates: A Bayesian modelling study in 143 European regions
Although seasonal variation has a known influence on the transmission of several respiratory viral infections, its role in SARS-CoV-2 transmission remains unclear. While there is a sizable and growing literature on environmental drivers of COVID-19 transmission, recent reviews have highlighted conflicting and inconclusive findings. This indeterminacy partly owes to the fact that seasonal variation relates to viral transmission by a complicated web of causal pathways, including many interacting biological and behavioural factors. Since analyses of specific factors cannot determine the aggregate strength of seasonal forcing, we sidestep the challenge of disentangling various possible causal paths in favor of a holistic approach. We model seasonality as a sinusoidal variation in transmission and infer a single Bayesian estimate of the overall seasonal effect. By extending two state-of-the-art models of non-pharmaceutical intervention (NPI) effects and their datasets covering 143 regions in temperate Europe, we are able to adjust our estimates for the role of both NPIs and mobility patterns in reducing transmission. We find strong seasonal patterns, consistent with a reduction in the time-varying reproduction number R(t) (the expected number of new infections generated by an infectious individual at time t) of 42.1% (95% CI: 24.7%—53.4%) from the peak of winter to the peak of summer. These results imply that the seasonality of SARS-CoV-2 transmission is comparable in magnitude to the most effective individual NPIs but less than the combined effect of multiple interventions.
- Top Cited PapersOpen Access
- 31 May 2022
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 119 (23)
Mask wearing in community settings reduces SARS-CoV-2 transmission
Significance: We resolve conflicting results regarding mask wearing against COVID-19. Most previous work focused on mask mandates; we study the effect of mask wearing directly. We find that population mask wearing notably reduced SARS-CoV-2 transmission (mean mask-wearing levels corresponding to a 19% decrease in R). We use the largest wearing survey (n = 20 million) and obtain our estimates from regions across six continents. We account for nonpharmaceutical interventions and time spent in public, and quantify our uncertainty. Factors additional to mask mandates influenced the worldwide early uptake of mask wearing. Our analysis goes further than past work in the quality of wearing data–100 times the size with random sampling–geographical scope, a semimechanistic infection model, and the validation of our results.
- 31 May 2022
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 119 (23)
Top Cited PapersOpen AccessMask wearing in community settings reduces SARS-CoV-2 transmission
Significance: We resolve conflicting results regarding mask wearing against COVID-19. Most previous work focused on mask mandates; we study the effect of mask wearing directly. We find that population mask wearing notably reduced SARS-CoV-2 transmission (mean mask-wearing levels corresponding to a 19% decrease in R). We use the largest wearing survey (n = 20 million) and obtain our estimates from regions across six continents. We account for nonpharmaceutical interventions and time spent in public, and quantify our uncertainty. Factors additional to mask mandates influenced the worldwide early uptake of mask wearing. Our analysis goes further than past work in the quality of wearing data–100 times the size with random sampling–geographical scope, a semimechanistic infection model, and the validation of our results.
- Top Cited PapersOpen Access
- 5 October 2021
- Published by Springer Nature in Nature Communications
- Vol. 12 (1) , 1-13
Understanding the effectiveness of government interventions against the resurgence of COVID-19 in Europe
European governments use non-pharmaceutical interventions (NPIs) to control resurging waves of COVID-19. However, they only have outdated estimates for how effective individual NPIs were in the first wave. We estimate the effectiveness of 17 NPIs in Europe’s second wave from subnational case and death data by introducing a flexible hierarchical Bayesian transmission model and collecting the largest dataset of NPI implementation dates across Europe. Business closures, educational institution closures, and gathering bans reduced transmission, but reduced it less than they did in the first wave. This difference is likely due to organisational safety measures and individual protective behaviours—such as distancing—which made various areas of public life safer and thereby reduced the effect of closing them. Specifically, we find smaller effects for closing educational institutions, suggesting that stringent safety measures made schools safer compared to the first wave. Second-wave estimates outperform previous estimates at predicting transmission in Europe’s third wave.
- 5 October 2021
- Published by Springer Nature in Nature Communications
- Vol. 12 (1) , 1-13
Top Cited PapersOpen AccessUnderstanding the effectiveness of government interventions against the resurgence of COVID-19 in Europe
European governments use non-pharmaceutical interventions (NPIs) to control resurging waves of COVID-19. However, they only have outdated estimates for how effective individual NPIs were in the first wave. We estimate the effectiveness of 17 NPIs in Europe’s second wave from subnational case and death data by introducing a flexible hierarchical Bayesian transmission model and collecting the largest dataset of NPI implementation dates across Europe. Business closures, educational institution closures, and gathering bans reduced transmission, but reduced it less than they did in the first wave. This difference is likely due to organisational safety measures and individual protective behaviours—such as distancing—which made various areas of public life safer and thereby reduced the effect of closing them. Specifically, we find smaller effects for closing educational institutions, suggesting that stringent safety measures made schools safer compared to the first wave. Second-wave estimates outperform previous estimates at predicting transmission in Europe’s third wave.
- Open Access
Mass mask-wearing notably reduces COVID-19 transmission
Mask-wearing has been a controversial measure to control the COVID-19 pandemic. While masks are known to substantially reduce disease transmission in healthcare settings [1–3], studies in community settings report inconsistent results [4–6]. Investigating the inconsistency within epidemiological studies, we find that a commonly used proxy, government mask mandates, does not correlate with large increases in mask-wearing in our window of analysis. We thus analyse the effect of mask-wearing on transmission instead, drawing on several datasets covering 92 regions on 6 continents, including the largest survey of individual-level wearing behaviour (n=20 million) [7]. Using a hierarchical Bayesian model, we estimate the effect of both mask-wearing and mask-mandates on transmission by linking wearing levels (or mandates) to reported cases in each region, adjusting for mobility and non-pharmaceutical interventions. We assess the robustness of our results in 123 experiments spanning 22 sensitivity analyses. Across these analyses, we find that an entire population wearing masks in public leads to a median reduction in the reproduction number R of 25.8%, with 95% of the medians between 22.2% and 30.9%. In our window of analysis, the median reduction in R associated with the wearing level observed in each region was 20.4% [2.0%, 23.3%] 1 . We do not find evidence that mandating mask-wearing reduces transmission. Our results suggest that mask-wearing is strongly affected by factors other than mandates. We establish the effectiveness of mass mask-wearing, and highlight that wearing data, not mandate data, are necessary to infer this effect.
Open AccessMass mask-wearing notably reduces COVID-19 transmission
Mask-wearing has been a controversial measure to control the COVID-19 pandemic. While masks are known to substantially reduce disease transmission in healthcare settings [1–3], studies in community settings report inconsistent results [4–6]. Investigating the inconsistency within epidemiological studies, we find that a commonly used proxy, government mask mandates, does not correlate with large increases in mask-wearing in our window of analysis. We thus analyse the effect of mask-wearing on transmission instead, drawing on several datasets covering 92 regions on 6 continents, including the largest survey of individual-level wearing behaviour (n=20 million) [7]. Using a hierarchical Bayesian model, we estimate the effect of both mask-wearing and mask-mandates on transmission by linking wearing levels (or mandates) to reported cases in each region, adjusting for mobility and non-pharmaceutical interventions. We assess the robustness of our results in 123 experiments spanning 22 sensitivity analyses. Across these analyses, we find that an entire population wearing masks in public leads to a median reduction in the reproduction number R of 25.8%, with 95% of the medians between 22.2% and 30.9%. In our window of analysis, the median reduction in R associated with the wearing level observed in each region was 20.4% [2.0%, 23.3%] 1 . We do not find evidence that mandating mask-wearing reduces transmission. Our results suggest that mask-wearing is strongly affected by factors other than mandates. We establish the effectiveness of mass mask-wearing, and highlight that wearing data, not mandate data, are necessary to infer this effect.
- Open Access
Seasonal variation in SARS-CoV-2 transmission in temperate climates
While seasonal variation has a known influence on the transmission of several respiratory viral infections, its role in SARS-CoV-2 transmission remains unclear. As previous analyses have not accounted for the implementation of non-pharmaceutical interventions (NPIs) in the first year of the pandemic, they may yield biased estimates of seasonal effects. Building on two state-of-the-art observational models and datasets, we adapt a fully Bayesian method for estimating the association between seasonality and transmission in 143 temperate European regions. We find strong seasonal patterns, consistent with a reduction in the time-variable R t of 42.1% (95% CI: 24.7% – 53.4%) from the peak of winter to the peak of summer. These results imply that the seasonality of SARS-CoV-2 transmission is comparable in magnitude to the most effective individual NPIs but less than the combined effect of multiple interventions.
Open AccessSeasonal variation in SARS-CoV-2 transmission in temperate climates
While seasonal variation has a known influence on the transmission of several respiratory viral infections, its role in SARS-CoV-2 transmission remains unclear. As previous analyses have not accounted for the implementation of non-pharmaceutical interventions (NPIs) in the first year of the pandemic, they may yield biased estimates of seasonal effects. Building on two state-of-the-art observational models and datasets, we adapt a fully Bayesian method for estimating the association between seasonality and transmission in 143 temperate European regions. We find strong seasonal patterns, consistent with a reduction in the time-variable R t of 42.1% (95% CI: 24.7% – 53.4%) from the peak of winter to the peak of summer. These results imply that the seasonality of SARS-CoV-2 transmission is comparable in magnitude to the most effective individual NPIs but less than the combined effect of multiple interventions.
- Top Cited PapersOpen Access
- 19 February 2021
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 371 (6531) , 802-+
Inferring the effectiveness of government interventions against COVID-19
How to hold down transmission: Early in 2020, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) transmission was curbed in many countries by imposing combinations of nonpharmaceutical interventions. Sufficient data on transmission have now accumulated to discern the effectiveness of individual interventions. Brauner et al. amassed and curated data from 41 countries as input to a model to identify the individual nonpharmaceutical interventions that were the most effective at curtailing transmission during the early pandemic. Limiting gatherings to fewer than 10 people, closing high-exposure businesses, and closing schools and universities were each more effective than stay-at-home orders, which were of modest effect in slowing transmission. Science , this issue p. eabd9338
- 19 February 2021
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 371 (6531) , 802-+
Top Cited PapersOpen AccessInferring the effectiveness of government interventions against COVID-19
How to hold down transmission: Early in 2020, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) transmission was curbed in many countries by imposing combinations of nonpharmaceutical interventions. Sufficient data on transmission have now accumulated to discern the effectiveness of individual interventions. Brauner et al. amassed and curated data from 41 countries as input to a model to identify the individual nonpharmaceutical interventions that were the most effective at curtailing transmission during the early pandemic. Limiting gatherings to fewer than 10 people, closing high-exposure businesses, and closing schools and universities were each more effective than stay-at-home orders, which were of modest effect in slowing transmission. Science , this issue p. eabd9338
- Open Access
How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
To what extent are effectiveness estimates of nonpharmaceutical interventions (NPIs) against COVID-19 influenced by the assumptions our models make? To answer this question, we investigate 2 state-of-the-art NPI effectiveness models and propose 6 variants that make different structural assumptions. In particular, we investigate how well NPI effectiveness estimates generalise to unseen countries, and their sensitivity to unobserved factors. Models that account for noise in disease transmission compare favourably. We further evaluate how robust estimates are to different choices of epidemiological parameters and data. Focusing on models that assume transmission noise, we find that previously published results are remarkably robust across these variables. Finally, we mathematically ground the interpretation of NPI effectiveness estimates when certain common assumptions do not hold.
Open AccessHow Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
To what extent are effectiveness estimates of nonpharmaceutical interventions (NPIs) against COVID-19 influenced by the assumptions our models make? To answer this question, we investigate 2 state-of-the-art NPI effectiveness models and propose 6 variants that make different structural assumptions. In particular, we investigate how well NPI effectiveness estimates generalise to unseen countries, and their sensitivity to unobserved factors. Models that account for noise in disease transmission compare favourably. We further evaluate how robust estimates are to different choices of epidemiological parameters and data. Focusing on models that assume transmission noise, we find that previously published results are remarkably robust across these variables. Finally, we mathematically ground the interpretation of NPI effectiveness estimates when certain common assumptions do not hold.
- Open Access
Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models
Recommending the best course of action for an individual is a major application of individual-level causal effect estimation. This application is often needed in safety-critical domains such as healthcare, where estimating and communicating uncertainty to decision-makers is crucial. We introduce a practical approach for integrating uncertainty estimation into a class of state-of-the-art neural network methods used for individual-level causal estimates. We show that our methods enable us to deal gracefully with situations of "no-overlap", common in high-dimensional data, where standard applications of causal effect approaches fail. Further, our methods allow us to handle covariate shift, where test distribution differs to train distribution, common when systems are deployed in practice. We show that when such a covariate shift occurs, correctly modeling uncertainty can keep us from giving overconfident and potentially harmful recommendations. We demonstrate our methodology with a range of state-of-the-art models. Under both covariate shift and lack of overlap, our uncertainty-equipped methods can alert decisions makers when predictions are not to be trusted while outperforming their uncertainty-oblivious counterparts.
Open AccessIdentifying Causal-Effect Inference Failure with Uncertainty-Aware Models
Recommending the best course of action for an individual is a major application of individual-level causal effect estimation. This application is often needed in safety-critical domains such as healthcare, where estimating and communicating uncertainty to decision-makers is crucial. We introduce a practical approach for integrating uncertainty estimation into a class of state-of-the-art neural network methods used for individual-level causal estimates. We show that our methods enable us to deal gracefully with situations of "no-overlap", common in high-dimensional data, where standard applications of causal effect approaches fail. Further, our methods allow us to handle covariate shift, where test distribution differs to train distribution, common when systems are deployed in practice. We show that when such a covariate shift occurs, correctly modeling uncertainty can keep us from giving overconfident and potentially harmful recommendations. We demonstrate our methodology with a range of state-of-the-art models. Under both covariate shift and lack of overlap, our uncertainty-equipped methods can alert decisions makers when predictions are not to be trusted while outperforming their uncertainty-oblivious counterparts.