Publications and Preprints

A General Language Assistant as a Laboratory for Alignment

December 2021

Askell, Amanda; Bai, Yuntao; Chen, Anna; Drain, Dawn; Ganguli, Deep; Henighan, Tom; Jones, Andy Joseph, Nicholas; Ben Mann, et al. A General Language Assistantas a Laboratory for Alignment. arXiv preprint arXiv:2112.00861 (2021)


Ensuring the Safety of Artificial Intelligence

November 2021

Askell, Amanda. ‘Ensuring the Safety of Artificial Intelligence’. In The Long View: Essays on policy, philanthropy, and the long-term future. Edited by Natalie Cargill and Tyler M. John. First Strategic Insight Ltd, 2021.


Language Models are Few-Shot Learners

May 2020

Brown, Tom; Mann, Ben; Ryder, Nick; Subbiah, Melanie et al. ‘Language Models are Few-Shot Learners.’ arXiv preprint arXiv:2005.14165 (2020).


Evidence Neutrality and the Moral Value of Information

September 2019

Askell, Amanda. ‘Evidence Neutrality and the Moral Value of Information’. In Effective Altruism: Philosophical Issues, edited by Hilary Greaves and Theron Pummer. Oxford: Oxford University Press, 2019.


Prudential Objections to Atheism

May 2019

Askell, Amanda. ‘Prudential Objections to Atheism’. In A Companion to Atheism and Philosophy, edited by Graham Oppy. Wiley-Blackwell, 2019.


Epistemic Consequentialism and Epistemic Enkrasia

January 2018

Askell, Amanda. ‘Epistemic Consequentialism and Epistemic Enkrasia’. In Epistemic Consequentialism, edited by Kristoffer Ahlstrom-Vij and Jeff Dunn. Oxford: Oxford University Press, 2018