Research
A selection of research conducted by pivotal fellows.
Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data
Nicola Croce (25.Q3 Fellow)
Benchmarking Deception Probes via Black-to-White Performance Boosts
Avi Parrack (25.Q1 Fellow)
ICML: Actionable Interpretability Workshop
Bayesian Influence Functions for Scalable Data Attribution
Philipp Alexander Kreer (25.Q1 Fellow)
ICML 2025: High-dimensional Learning Dynamics
Factored Cognition Strengthens Monitoring and Thwarts Attacks
Aaron Sandoval (25.Q1 Fellow)
Understanding the learned look-ahead behavior of chess neural networks
Diogo Cruz (2024 Fellow)
Forging the Biological Weapon Convention: A Brief History of the Creation of the BWC
Neha Suresh (25.Q1 Fellow)
The Pandora Report
Will the US Government Control the First AGI?—Finding Base Rates
Luise Woehlke (2024 Fellow)
Sharing the AI Windfall: A Strategic Approach to International Benefit-Sharing
Michel Justen (2024 Fellow)
The Role of AI Safety Institutes in Contributing to International Standards for Frontier AI Safety
Kristina Fort (2024 Fellow)
On Labs and Fabs: Mapping How Alliances, Acquisitions, and Antitrust are Shaping the Frontier AI Industry
Tomás Aguirre (2023 Fellow)