Caltech
Stanford University
Daniel MurfetCo-founder · ResolutionResearcher↗Both at Resolution
Researcher · Founder · Policy · Executive
Geoffrey Irving
ResolutionCofounder and Chief Scientist
Irving co-developed AI debate, a proposal in which competing systems try to expose weaknesses in each other's answers so a human can judge problems too complex to solve alone.[1] His later work builds open-ended evaluations that search for unexpected frontier-model capabilities and failures.
Career & education
Current roleResolution2026-presentCofounder and Chief Scientist
Resolution2026-presentPreviously
AI Security Institute2024-2026Chief Scientist
Google DeepMind2019-2023Director
OpenAI2017-2019Member of Technical Staff
Google Brain2015-2017Software Engineer
AI Security Institute2024-2026Google DeepMind2019-2023OpenAI2017-2019Google Brain2015-2017Education
Work 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.
citations105,035As of Aug 1, '26
citations+1,597Since last snapshot, Jul 1, '26
Updates 2
New orgResolution added to the database
The nonprofit alignment research organization founded by Geoffrey Irving and Daniel Murfet, originally announced as Sequent, is now tracked as Resolution.
June 10, 2026MoveGeoffrey Irving leaves AISI to start alignment nonprofitIrving said he will leave AISI soon, move back to the Bay Area, and start a new nonprofit alignment research organization.
May 15, 2026References
- AI Safety via Debatearxiv.org
Irving, Christiano and Amodei propose training competing systems to help a human judge a complex answer.
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 August 8, 2026 · Checked for accuracy and new information.