Hi, I'm Ben! I'm currently a Member of Technical Staff at Geodesic Research in London, researching pre-training and mid-training safety interventions. Before that, I was a Pivotal research fellow studying personas and multi-agent interactions under Cozmin Ududec at UK AISI.
I finished my master's degree at MIT earlier this year, where I studied EECS and entrepreneurship and was part of MIT AI Alignment (MAIA). Before grad school, I spent four years as a software engineer at Amazon, working on routing and optimization for their truck and train fleets across North America and Europe. And before that, I studied computer science and economics at Georgetown, where I was a George F. Baker Scholar.
Outside of my work at Geodesic, my research interests include societal impacts of AI (unintentional human influence), behavioral evals (sycophancy and personas), and multi-agent communication.
Hobbies: I love building mechanical keyboards, playing sports (badminton, archery, skiing, squash), and cooking & baking. I attended culinary school part-time while working in New York, though I never quite finished. Happy to chat!
Research
* indicates equal contribution.
Out-of-Distribution Generalization of Risk Aversion in Language Models
Kristina Zhang*, Junior Chinomso Okoroafor*, Benjamin Maltbie*, Andrew Lin*, Abhitej Bokka*, Elliott Thornley
2026. Published at ICML'26 Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD).
Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models
Benjamin Maltbie, Shivam Raval
Preprint. 2026.
Agentic Reinforcement Learning for Competitor-Aware Customer Retention
Benjamin Maltbie
Master's Thesis. Preprint. 2026.
Writing
Sycophancy: A Systemic, Catastrophic Risk(-Factor)
Arguing that sycophancy, left unaddressed, could cascade into a catastrophic risk to humanity.
Experience
Oct 2026 – Present
Geodesic Research
Member of Technical Staff
Pre-training & mid-training interventions
2026 Q3
Pivotal Research
Research Fellow
Researching personas and multi-agent interactions in long context settings under Cozmin Ududec (UK AISI)
2024 – 2026
MIT
M.S. & MBA Student
Electrical Engineering & Computer Science (EECS), Leaders for Global Operations (LGO)
During MIT
MIT Schwarzman College of Computing
SERC Research Fellow · 2025 – 2026
Training reward models to instill risk-aversion in open-source models
Supervised Program for Alignment Research
Research Fellow · 2025
Investigating complex persona and sycophancy interactions
Verizon
Master's Thesis · 2025
Agentic Reinforcement Learning for Competitor-Aware Customer Retention
2020 – 2024
Amazon
Software Engineer
Transportation Optimization (MMPO)
2016 – 2020
Georgetown University
B.S. & B.A. Student
Computer Science & Economics.
George F. Baker Scholar
During Georgetown
Jane Street
Strategy & Product Intern · 2019
Previously called Business Development
Maxlab: Laboratory for Computational Cognitive Neuroscience
Research Assistant · 2017 – 2019
Leveraging Prior Concept Learning Improves Generalization From Few Examples in Computational Models of Human Object Recognition
