David Duvenaud

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

arXiv 2024

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

arXiv 2024

Alignment faking in large language models

arXiv 2024

Residual Flows for Invertible Generative Modeling

residual-flows-for-invertible-generative-2

Explaining Image Classifiers by Counterfactual Generation

explaining-image-classifiers-by-1

Isolating Sources of Disentanglement in Variational Autoencoders

isolating-sources-of-disentanglement-in-1

Convolutional Networks on Graphs for Learning Molecular Fingerprints

convolutional-networks-on-graphs-for-learning-1

Buck Shlegeris

Carson Denison

Ethan Perez

Evan Hubinger

Jared Kaplan

co-founder / Chief Science Officer

Monte MacDiarmid

Samuel R. Bowman

Fazl Barez

Nicholas Schiefer

Ricky T. Q. Chen