LLMpeople
Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Amanda Askell

Amanda Askell is a philosopher and AI alignment researcher at Anthropic. Her personal site says she previously worked as a research scientist on the policy team at OpenAI.

Research scientist in alignment finetuning at Anthropic.2 organizations7 reports

Profile status: updated

updated 2 public sources
philosophyAI alignmentfinetuning

Current frame

Research scientist in alignment finetuning at Anthropic.

Education

New York University PhD · Philosophy 2011 → 2018
University of Oxford BPhil · Philosophy 2009 → 2011
University of Dundee MA (Hons) · Philosophy 2005 → 2009

Work

Anthropic Research Scientist (Alignment Finetuning)
OpenAI Research Scientist (Policy)

Public links

website Personal website github GitHub profile google_scholar Google Scholar profile linkedin LinkedIn profile x X profile

Organizations

core OpenAI core Anthropic

Reports

Alignment and Safety Auditing language models for hidden objectives Alignment and RLHF Collective Constitutional AI: Aligning a Language Model with Public Input Alignment and RLHF Constitutional AI: Harmlessness from AI Feedback Alignment and Safety Constitutional Classifiers++: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Large Language Models Language Models are Few-Shot Learners Alignment and Safety Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training Alignment and RLHF Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Official and primary sources

About Me | Amanda Askell Official source · homepage · Amanda Askell

Supporting sources

Curriculum Vitae | Amanda Askell Supporting source · other · Amanda Askell