All people
JM

Researcher

Julian Michael

MetaAI Safety, Evaluation and Alignment

Michael studies scalable oversight: ways for people to supervise AI systems on tasks too difficult to check directly. His work uses debate and demanding benchmarks such as GPQA to test whether models can be evaluated reliably.

Career & education

Current role
AI Safety, Evaluation and Alignment
Previously
Head of Safety, Evaluations and Alignment Lab

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.
2 snapshots
Citation history from Aug 25, '25 to Jun 15, '2622,04718,88015,713Aug 252025Jun 152026
citations22,047As of Jun 15, '26
citations+6,334Since last snapshot, Aug 25, '25
For today’s citation count and per work, visit Google Scholar.
About this profile

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 12, 2026 · Checked for accuracy and new information.

Sharing card

Related people