(conversations are logged)

Hi, I’m Alex Loftus. I build and run 0-to-1 technical programs at the intersection of AI safety research and engineering — most recently leading multi-agent red-teaming campaigns for OpenAI: recruiting the team, designing the research, building the evaluation infrastructure, and running live operations end-to-end. I’m also a textbook author, Kaggle competition winner, and PhD researcher with David Bau’s group, where I study interpretability and evaluation for large language models. Before this I worked as a data scientist, a machine learning engineer, and a master’s student in biomedical machine learning at Johns Hopkins University.

I’ve been fortunate to work with a number of brilliant people over the years. Here are some fun projects which resulted:

• I designed and led an internal red-teaming campaign for OpenAI — writing the proposal, recruiting the 16-person team, and building ~17K lines of evaluation infrastructure in under two weeks. The project was successful enough that a second campaign is now underway, with double the team size.
• I’m a co-author of Agents of Chaos, which was covered by Science and WIRED, featured in Anthropic co-founder Jack Clark’s Import AI, and went viral on X (millions of views).
• I helped organize the New England Mechanistic Interpretability (NEMI) conference to help build the interpretability community in the Northeast.
• I helped out with some work on Subliminal Learning, which got featured in a Welsh labs YouTube video
• I led the publication effort for NDIF, a large-scale AI interpretability infrastructure project, which led to a paper at ICLR.
• I’ve given talks for the San Diego Machine Learning meetup group, where I joined a team competing in the Vesuvius Ink Detection Kaggle Competition. We won 1st place against 1,249 teams for a competition prize pool of $100,000. Our work was featured in Scientific American!
• I worked with Professor Joshua Vogelstein in the Johns Hopkins Biomedical Engineering department on a pipeline to create graphs from MRI data, which led to a paper in-review at Nature Methods.
• We developed an open-source project, Graspologic, which was acquired by Microsoft and used to measure collaboration changes in their workforce during COVID.
• I made a linear algebra tutoring series for my friend, which builds up the mathematical machinery of neural networks starting from the absolute foundations: dot product geometry and linear algebra.

I have a number of academic side-interests, including spectral theory, information geometry, the history of science and mathematics, the mechanics of the visual system, constitutional law, various causal relationships between geography and history, and ethics (I am a big fan of Kant, Hume, Ross, and some modern ethicists like Susan Wolf). I am an avid traveler and am (slowly) learning Spanish.

Misc

I grew up in Seattle, WA. I was a competitive Starcraft 2 player in high school (grandmaster league - competed/won in seattle-area tournaments!). I studied behavioral neuroscience during my undergraduate years, with a philosophy minor focused on ethics. I got interested in math and programming and started a computational neuroscience club, where I taught weekly seminars. I also spent a lot of time partner dancing and playing guitar at open mic nights!

Set up a meeting with me here: calendly.com/alexloftus2004