University of Oxford
University of Cambridge
Ajeya CotraMember of Technical Staff · METRResearcher↗
Researcher
Joe Benton
METREmbedded assessment of AI risks
Benton studies how to assess and reduce risks from advanced AI. At Anthropic he led work on scalable oversight—ways to supervise systems that may outperform people—and researched tests for deceptive or misaligned behavior; he joined METR to develop independent, embedded risk assessments.
Career & education
Current roleMETRAug 2026-presentEmbedded assessment of AI risks
METRAug 2026-presentPreviously
AnthropicNov 2023-Aug 2026Member of Technical Staff; Manager, Scalable Oversight
AI Security InstituteFall 2023-Fall 2023Technical Staff, UK Frontier AI Taskforce
Redwood ResearchWinter 2022-2023Machine Learning Researcher
AnthropicNov 2023-Aug 2026AI Security InstituteFall 2023-Fall 2023Redwood ResearchWinter 2022-2023Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations2,853As of Sep 6, '26
Updates 1
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed September 6, 2026 · Checked for accuracy and new information.
