hi! im tim
i build and study ML systems
these days im thinking about how models work internally and how to make their behavior more transparent and reliable
what i've been up to:
2025
investigating entity representations in transformer LMs · CHAI
2023–24
MEng CS · MIT
2019–23
BS Physics & BS CS · MIT
reach me at:
Selected Publications
CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
Benjamin Arnav*, Pablo Bernabeu-Pérez*, Nathan Helm-Burger*, Timothy H. Kostolansky*, Hannes Whittingham*, Mary Phuong