Ben Maltbie

Hi! I am currently a research fellow at Pivotal Research investigating personas and multi-agent interactions in long context settings with black-box techniques. My research mentor is Cozmin Ududec who leads the Science of Evaluation team at the UK AISI.

I just finished my master's degree at MIT where I studied EECS and entrepreneurship and was a member of MIT AI Alignment (MAIA). Before MIT, I worked as a software engineer at Amazon on truck/train routing algorithms and large scale optimization problems for their fleet across North America and Europe. I completed my undergrad at Georgetown University where I double majored in computer science and economics and was a George F. Baker Scholar.

In the past year, I've been transitioning into working full-time as an AI safety researcher. My research interests are on societal impacts of AI, behavioral evals (particularly sycophancy and diverse personas), and black-box control. My experience so far is largely with multi-turn evals, training reward models, and red-teaming.

Hobbies: I love building mechanical keyboards, doing different sports (badminton, archery, skiing, squash), and cooking & baking (I attended culinary school part-time after work while in NY, though never finished). Happy to chat!