Jane Street
University of Cambridge
University of Leeds
Eric NeymanResearcher · Alignment Research CenterResearcher↗
Researcher · Executive
Jacob Hilton
Alignment Research CenterVP of Research
Hilton studies how to understand and control advanced neural networks. At OpenAI he worked on truthful assistants, reinforcement learning from human feedback and reward-model overoptimization; at ARC he develops theory for explaining model behavior.
Career & education
Current roleAlignment Research Center2023-presentVP of Research
Alignment Research Center2023-presentPreviously
OpenAI2018-2023Researcher
OpenAI2018-2023Work 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.
citations56,705As of Oct 19, '26
citations+10,771Since last snapshot, Jun 15, '26
Selected contributions
Training Language Models to Follow Instructions with Human Feedback
With Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang and others ·InstructGPT uses human feedback to train language models to follow instructions.
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 9, 2026 · Checked for accuracy and new information.
