Nathaniel Monson
Bio
Nathaniel B. Monson is a Founding Research Scientist at Guide Labs, a product-focused research company building inherently interpretable large language models. He holds a Ph.D. in Mathematics from the University of Maryland, College Park, where his dissertation focused on computational topology including an approximation theorem on persistent homology, and a B.A. with High Honors from Swarthmore College. He transitioned into AI interpretability research in Autumn 2022, supported by a Long-Term Future Fund grant and a Lightspeed grant, with a focus on using mechanistic interpretability tools to extract objective functions from complex models and addressing polysemanticity in neural networks. On LessWrong and the Alignment Forum, he writes about AI alignment topics including mechanistic interpretability and long-term AI safety. Guide Labs, where he is a founding team member, recently open-sourced Steerling-8B, an 8-billion-parameter LLM designed so that every token produced can be traced back to its origins in training data.
Links
- Personal Website
- https://nmonson1.github.io/
- Twitter / X
- LessWrong
- nathaniel-monson
Grants
from Long-Term Future Fund
Discussion
Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.
Details
- Last Updated
- Mar 22, 2026, 11:47 PM UTC
- Created
- Mar 20, 2026, 2:55 AM UTC