Toby Shevlane

540

270

135

405

202020212022202320247 16 8 133 527

Vijay BolinaGoogle DeepMindVerified email at google.com
Allan DafoePrincipal Scientist (Director), Google DeepMindVerified email at google.com
Divya SiddarthMicrosoft ResearchVerified email at microsoft.com
Markus AnderljungCentre for the Governance of AIVerified email at governance.ai
Jade LeungResearcher, Centre for the Governance of AI, Future of Humanity Institute, University of OxfordVerified email at governance.ai
Mary PhuongIST AustriaVerified email at ist.ac.at
Ben GarfinkelDirector, Centre for the Governance of AI; Research Fellow, University of OxfordVerified email at philosophy.ox.ac.uk
Will HawkinsDeepMindVerified email at deepmind.com
Shahar AvinUniversity of CambridgeVerified email at cam.ac.uk
Sebastian FarquharGoogle DeepMindVerified email at google.com
Iason GabrielStaff Research Scientist, DeepMindVerified email at google.com
Jess WhittlestoneSenior Research Associate, Centre for the Study of Existential Risk, University of CambridgeVerified email at cam.ac.uk
Paul ChristianoNational Institute of Standards and TechnologyVerified email at nist.gov
Yoshua BengioProfessor of computer science, University of Montreal, Mila, IVADO, CIFARVerified email at umontreal.ca
Carina PrunklInstitute for Ethics in AI, University of OxfordVerified email at philosophy.ox.ac.uk
Yarin GalAssociate Professor, University of OxfordVerified email at cs.ox.ac.uk
Jan LeikeOpenAIVerified email at openai.com

Toby Shevlane

Google DeepMind

Verified email at google.com


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ... arXiv preprint arXiv:2312.11805, 2023	503	2023
Model evaluation for extreme risks T Shevlane, S Farquhar, B Garfinkel, M Phuong, J Whittlestone, J Leung, ... arXiv preprint arXiv:2305.15324, 2023	94*	2023
Structured access: an emerging paradigm for safe AI deployment T Shevlane arXiv preprint arXiv:2201.05159, 2022	46	2022
The Offense-Defense Balance of Scientific Knowledge: Does Publishing AI Research Reduce Misuse? T Shevlane, A Dafoe Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 173-179, 2020	41*	2020
Contact tracing apps can help stop coronavirus. But they can hurt privacy T Shevlane, B Garfinkel, A Dafoe The Washington Post, 2020	6	2020
Evaluating Frontier Models for Dangerous Capabilities M Phuong, M Aitchison, E Catt, S Cogan, A Kaskasoli, V Krakovna, ... arXiv preprint arXiv:2403.13793, 2024	3*	2024
A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI S El-Sayed, C Akbulut, A McCroskery, G Keeling, Z Kenton, Z Jalan, ... arXiv preprint arXiv:2404.15058, 2024	2	2024
The Artefacts of Intelligence: Governing Scientists' Contribution to AI Proliferation T Shevlane University of Oxford, 2022	2	2022

The system can't perform the operation now. Try again later.

Articles 1–8

Citations per year