Harvey Mudd College
Neev ParikhAnthropicResearcher↗
Researcher · Executive
Evan Hubinger
AnthropicMember of Technical Staff, Manager
Hubinger helped define the problem of inner alignment: whether a trained model develops its own internal objective rather than the one intended by its designers.[1] At Anthropic he leads alignment stress-testing, probing models for deceptive behavior, hidden goals and sabotage risks before deployment.[2]
Career & education
Current roleAnthropicJan 2023-presentMember of Technical Staff, Manager
AnthropicJan 2023-presentPreviously
Machine Intelligence Research InstituteNov 2019-Jan 2023Research Fellow
Machine Intelligence Research InstituteNov 2019-Jan 2023Education
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.
citations8,608As of Oct 11, '26
citations+2,863Since last snapshot, Jun 15, '26
References
- Risks from Learned Optimization in Advanced Machine Learning Systemsarxiv.org
Co-authorship and foundational analysis of learned internal objectives and inner alignment.
- Anthropic Residency — mentors and research areasalignment.anthropic.com
Explicitly identifies Evan Hubinger as leading the Alignment Stress-Testing team.
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 10, 2026 · Checked for accuracy and new information.
