Skip to main content

Scott Emmons

Research Scientist

Google DeepMind

Scott Emmons previously cofounded FAR.AI and served as a Research Advisor. He is now a research scientist at Google DeepMind focused on AI safety and alignment.

Publications

Uncovering Latent Human Wellbeing in Language Model Embeddings

Interpretability

Do language models implicitly learn a concept of human wellbeing? We explore this through the ETHICS Utilitarianism task, assessing if scaling enhances pretrained models' representations.

February 18, 2024
Date Range

imitation: Clean Imitation Learning Implementations

Alignment

We describe a software package called "imitation" which provides PyTorch implementations of several imitation and reward learning algorithms, including three inverse reinforcement learning algorithms, three imitation learning algorithms, and a preference comparison algorithm.

September 21, 2022
Date Range

News

Uncovering Latent Human Wellbeing in LLM Embeddings

Red-Teaming & Evaluation

A one-dimensional PCA projection of OpenAI's `text-embedding-ada-002` model achieves 73.7% accuracy on the ETHICS Util test dataset.

September 11, 2023
Date Range

Research

Our research explores a portfolio of high-potential agendas.

Events

Our events bring together global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI