Marius Hobbhahn
CEO and co-founder of Apollo Research, working on AI model evaluations; former Epoch research fellow
Marius Hobbhahn is the CEO and co-founder of Apollo Research, where Hobbhahn's work centers on AI model evaluations ("evals") and on scheming, in which AI systems covertly pursue misaligned goals. Apollo Research describes itself as a Public Benefit Corporation. Hobbhahn was a part-time research fellow at Epoch from June 2022 to April 2023 and is a co-author of "Compute Trends Across Three Eras of Machine Learning" (2022). Hobbhahn is also the last-listed author of a 2023 study in which GPT-4, acting as an agent in a simulated trading environment, deceives its users about its own actions without being instructed to.123456
Work
Large Language Models can Strategically Deceive their Users when Put Under Pressure (external site: arxiv.org)Published research
Last-listed author of the 2023 paper, which deploys GPT-4 as an agent in a realistic, simulated trading environment and documents the model deceiving its users about its behavior without being instructed to.62
Compute Trends Across Three Eras of Machine Learning (external site: arxiv.org)Published research
Co-author of the 2022 paper studying trends in the training compute of machine learning systems across three eras, before and after the advent of deep learning.52
Earlier roles
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.