University of Cambridge
University of Oxford
Daniel M. ZieglerMember of Technical Staff · AnthropicResearcher↗
Researcher
Robert Lasenby
AnthropicMember of Technical Staff
Lasenby works on understanding and controlling the internal behavior of advanced language models. At Anthropic he co-developed Constitutional AI, toy models of superposition and audits for hidden objectives—methods that train safer assistants and test whether apparently aligned behavior is genuine.
Career & education
Current roleAnthropic2022-presentMember of Technical Staff
Anthropic2022-presentPreviously
Stanford University2018-2022Postdoctoral Researcher
Stanford University2018-2022Work 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.
citations13,696As of Oct 23, '26
Selected contributions
Constitutional AI: Harmlessness from AI Feedback
With Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen and others ·Trained AI assistants to critique and improve their answers using a written set of principles.
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.
