OpenAI
University of Oxford
New York University
Evan HubingerMember of Technical Staff, Manager · AnthropicResearcher↗
Researcher
Amanda Askell
AnthropicResearch Scientist (Alignment Finetuning)
Askell brings philosophy into AI training, shaping how Claude handles honesty, uncertainty and difficult choices.[1] She is the primary author of Claude’s 2026 constitution, a detailed statement of intended values and behavior used in training, translating ethical ideas into guidance for an AI assistant.[2]
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.
citations250,868As of Nov 1, '26
citations+10,825Since last snapshot, Oct 1, '26
Selected contributions
Language Models are Few-Shot Learners
With Tom Brown, Ben Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan and others ·GPT-3 performs tasks from prompts and a few examples without task-specific training.
Learning Transferable Visual Models From Natural Language Supervision
With Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry and others ·CLIP learns from image-caption pairs to recognize categories described in words.
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.
References
- Amanda Askell — personal siteaskell.io
Philosophy background, model honesty and character-training work.
- Claude’s Constitutionanthropic.com
Primary authorship, majority of text, character work and use in training.
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.
