Samuel Nellessen

Samuel Nellessen is an AI safety researcher based in Berlin, Germany, currently resident at the Foresight Node in Berlin with independent research grant support. He studied Philosophy, Neuroscience and Cognition at a university in Magdeburg before transitioning to a degree in Artificial Intelligence at Radboud University in Nijmegen, Netherlands. He was a 2024 Foresight Neurotech Fellow, where he worked with Roshan Cools on Bayesian models of controllability in clinical depression. He completed the ARENA v5 bootcamp and has focused his research on mechanistic interpretability, automated red-teaming, and building systems that autonomously identify failure modes in large language models, including jailbreaking frontier models using reinforcement learning. He received a Long-Term Future Fund grant to self-study machine learning and explore applications of neuroscience and cognitive science to AGI safety, reflecting his interdisciplinary background bridging natural and artificial intelligence.

Personal Website

https://samuelnellessen.com/

LinkedIn

LinkedIn

Twitter / X

Twitter

LessWrong

samuel-nellessen

EA Forum

-

Projects

No grants recorded.