Amanda Askell

Extracted Attributes

• Honors

  Time 100 AI list (2024)

• Education

  PhD in Philosophy (New York University), BPhil in Philosophy (University of Oxford), MA in Philosophy (University of Dundee)

• Occupation

  Philosopher, AI Researcher

• Nationality

  Scottish

• Current Role

  Head of Personality Alignment at Anthropic

• Notable Works

  Constitutional AI framework

Timeline

• Began her undergraduate studies in Philosophy at the University of Dundee, graduating in 2009. (Source: Web search results)

  2005-09-01

• Began her BPhil in Philosophy at the University of Oxford, graduating in 2011. (Source: Web search results)

  2009-09-01

• Began her PhD in Philosophy at New York University, graduating in 2018. (Source: Web search results)

  2011-09-01

• Joined OpenAI as a Research Scientist focusing on Policy and Ethics. (Source: Web search results)

  2018-01-01

• Became Co-Chair of the Partnership on AI's Safety-Critical AI Working Group. (Source: Web search results)

  2019-01-01

• Left OpenAI and joined Anthropic to lead the personality alignment team. (Source: Wikipedia)

  2021-01-01

• Named to the Time 100 AI list in recognition of her contributions to AI safety and alignment. (Source: Wikipedia)

  2024-01-01

Amanda Askell

Amanda Askell (née Hall; formerly MacAskill; born 1988 or 1989) is a Scottish philosopher and AI researcher. She has served as the head of the personality alignment team at Anthropic since 2021. She has played a large role in the development of Claude's personality and constitution. In 2024, she appeared on the Time 100 AI list. She previously worked at OpenAI, but left over concerns that the company was not prioritizing AI safety enough. She has published over 60 papers and has received over 190,000 citations.

Web Search Results

• Amanda Askell - Wikipedia

  Amanda Askell (née Hall; formerly MacAskill; born 1988 or 1989) is a Scottish philosopher and AI researcher. She has served as the head of the personality alignment team at Anthropic since 2021. She has played a large role in the development of Claude "Claude (language model)")'s personality and constitution. In 2024, she appeared on the Time 100 AI list. She previously worked at OpenAI, but left over concerns that the company was not prioritizing AI safety enough. She has published over 60 papers and has received over 190,000 citations. ## Early life and education [...] ### Constitutional AI Askell has been a key contributor to the development of Constitutional AI (CAI), a method for training AI systems to meet the standards of harmlessness and helpfulness using AI feedback rather than extensive human oversight. The approach involves providing AI models with a set of principles, or "constitution", to guide their behavior, allowing them to critique and revise their own responses based on these principles. [...] | Notable works | Constitutional AI framework | | Notable ideas | Constitutional AI AI personality alignment Infinite ethics | | | | | Website | askell.io |

• ‪Amanda Askell‬ - ‪Google Scholar‬

  Amanda Askell [...] | Release strategies and the social impacts of language models I Solaiman, M Brundage, J Clark, A Askell, A Herbert-Voss, J Wu, ... arXiv preprint arXiv:1908.09203, 2019 | 1032 | 2019 | | In-context learning and induction heads C Olsson, N Elhage, N Nanda, N Joseph, N DasSarma, T Henighan, ... arXiv preprint arXiv:2209.11895, 2022 | 1014 | 2022 | | Toward trustworthy AI development: mechanisms for supporting verifiable claims M Brundage, S Avin, J Wang, H Belfield, G Krueger, G Hadfield, H Khlaaf, ... arXiv preprint arXiv:2004.07213, 2020 | 912 | 2020 | | A general language assistant as a laboratory for alignment A Askell, Y Bai, A Chen, D Drain, D Ganguli, T Henighan, A Jones, ... arXiv preprint arXiv:2112.00861, 2021 | 858 | 2021 | [...] | Advances in neural information processing systems T Brown, B Mann, N Ryder, M Subbiah, JD Kaplan, P Dhariwal, ... Language models are few-shot learners 33, 1877-901, 2020 | 2164 | 2020 | | Language models (mostly) know what they know S Kadavath, T Conerly, A Askell, T Henighan, D Drain, E Perez, ... arXiv preprint arXiv:2207.05221, 2022 | 1410 | 2022 | | Language models are few-shot learners. arXiv TB Brown, B Mann, N Ryder, M Subbiah, J Kaplan, P Dhariwal, ... arXiv preprint arXiv:2005.14165 10, 2020 | 1381 | 2020 | | Towards monosemanticity: Decomposing language models with dictionary learning T Bricken, A Templeton, J Batson, B Chen, A Jermyn, T Conerly, N Turner, ... Transformer Circuits Thread 2 (5), 6, 2023 | 1249 | 2023 |

• [PDF] Amanda Askell

  Amanda Askell email: amanda@askell.io Employment and Professional Roles 2018 - Present Research Scientist (Policy & Ethics) at OpenAI 2019 - Present Co-Chair of Partnership on AI’s Safety-Critical AI Working Group Education PhD in Philosophy​, New York University (2011 - 2018) Pareto Principles in Infinite Ethics, Cian Dorr (advisor), David Chalmers, Shelly Kagan BPhil in Philosophy​, University of Oxford (2009 - 2011) MA (Hons) in Philosophy,​ University of Dundee (2005 - 2009) Areas of Specialization ​AI Policy and Ethics Formal Ethics Decision Theory Publications ​AI safety needs social scientists, with Geoffrey Irving, ​Distill,​ 2019. Evidence Neutrality and the Moral Value of Information, ​Effective Altruism: Philosophical Issues​, H. Greaves and T. Pummer (Editors), Oxford [...] Spring 2013, Lecturer: Dan Greco Selected Academic Awards & Scholarships Young Ethicists Prize (with Tyler John), Rocky Mountain Ethics Congress, 2017 Mellon Dissertation Fellowship in Philosophy 2016 - 2017 Henry M. MacCracken PhD Fellowship 2011 - 2016 AHRC Research Preparation Masters Scholarship 2009 - 2011 Public Engagement Given talks for AI events such as the AI Salon at Stanford AI Laboratory and Girl Geek X Guest on podcasts like Rationally Speaking and The 80,000 Hours Podcast [...] Issues​, H. Greaves and T. Pummer (Editors), Oxford University Press, 2019. Prudential Objections to Atheism, ​The Blackwell Companion to Atheism and Philosophy​, G. Oppy (Editor), Wiley-Blackwell, 2019. Epistemic Consequentialism and Epistemic Enkrasia, ​Epistemic Consequentialism​, K. Ahlstrom-Vij and J. Dunn (Editors), Oxford University Press, 2018. Reports and Pre-Prints ​Release Strategies and the Social Impacts of Language Models, Solaiman et al., arXiv preprint, ​arXiv:1908.09203​, Aug 2019. The Role of Cooperation in Responsible AI Development, with Miles Brundage and Gillian Hadfield, arXiv preprint, arXiv:1907.04534, Jul 2019. Selected Presentations Having our cake and eating it too: How to develop AI competitively without falling victim to collective action problems, ​Berkman

• About Me | Amanda Askell

  # About Me I’m a philosopher working on finetuning and AI alignment at Anthropic. My team trains models to be more honest and to have good character traits, and works on developing new finetuning techniques so that our interventions can scale to more capable models. Before this I worked as a research scientist on the policy team at OpenAI, where I worked on AI safety via debate and human baselines for AI performance. [...] I have a PhD in philosophy from NYU with a thesis on infinite ethics and a BPhil in philosophy from the University of Oxford. I did my undergraduate degree in Philosophy at the University of Dundee, where I started out my academic life as a fine art and philosophy student at the Duncan of Jordanstone art school. My philosophy work has mostly revolved around ethics, decision theory, and formal epistemology. I’m a member of Giving What We Can and I’ve pledged to donate at least 10% of my lifetime income to charity, but I hope to make that more than 50% if I can. I donate primarily to global poverty charities. Amanda Amanda

• A Letter To Amanda Askell - by Jurgen Gravestein

  This ‘conceptual borrowing’, claiming one process analogous to another, is happening constantly and callously in the field of AI. Not only can we observe that the over-anthropomorphic interpretation of computational systems is likely the result of a poor understanding the human mind, it also actively contributes to the confusion between the two. [...] ### Dear Amanda, With much curiosity, I have read the new constitution of Claude. As a writer, I can see that it has been crafted with extraordinary care and attention to detail. The comprehensiveness of the document betrays a deep commitment to the work that you’ve been asked to do, and the responsibility you and many others within Anthropic feel to get it right. [...] I’ve been writing about this as part of a larger “AI eschatology” cycle, and one thing that’s shifted my thinking recently is how dense the ethics, funding, staffing, and governance networks actually are. What first looked like Baptists and bootleggers is starting to look more like a vertically integrated priesthood. Same ecosystem doing the theology, the money, and the institutional legitimation, then downplaying the label when it’s inconvenient. That doesn’t make anyone a villain. But it does mean the problem isn’t the constitution’s tone or metaphors. It’s the structural role the constitution plays.

• Gender

  female

• Educated At

  University of Oxford

• Instance Of

  Q5

• Occupation

  philosopher