Lukas Galke Poech | Tracing connectionist mechanisms for safer AI systems.

Lukas Galke Poech

Assistant Professor
University of Southern Denmark (SDU)
Faculty of Science
Department of Mathematics and Computer Science (IMADA)
Data Science Section
Center for Machine Learning
Affiliate member of the Pioneer Centre for Artificial Intelligence (P1)

My research advances AI safety by investigating how and why the most powerful AI systems behave the way they do.

News

  • November 2025: The MIST project on mechanistic interpretability for safe LLM agents has been funded by the Novo Nordisk Foundation. I am now hiring at PhD and Postdoc level—get in touch if you're interested.
  • November 2025: FlexDeMo has been accepted to AAAI 2026.
  • October 2025: Culture Neurons have been accepted to AACL-IJCNLP 2025 Findings.

Contact: lukas 'at' lpag.de
Design: Adapted from Diane Mounter.
Privacy: No personal data, no cookies.