Researcher
Tomek Korbak
Current role not listed
Korbak studies how to detect deception or misbehavior in AI systems by monitoring their written reasoning. He co-led the Chain of Thought Monitorability paper, which argues that this reasoning offers a promising but fragile opportunity to oversee powerful AI.
Career & education
Previously
OpenAINov 25-2026Member of Technical Staff
AI Security Institute2024-2025Senior Research Scientist
Anthropic2023-2024Member of Technical Staff
OpenAINov 25-2026AI Security Institute2024-2025Anthropic2023-2024
University of Warsaw
University of SussexWork 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.
citations7,993As of Jun 14, '26
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 October 2, 2026 · Checked for accuracy and new information.