AI Safety

• Research on AI Safety
• Empirically analyzing machine behavior and emergent abilities in large language models
• Investigating the ramifications of intelligent systems, in particular generative AI, for different fields of society
• Exploring the overlap between machine learning approaches and insights from cognitive science

Project are funded by:

Coefficient Giving "Investigating Dimensions of Deception Abilities in Language Models"

Schmidt Sciences "Investigating Hawthorne Effects in Large Reasoning Models"

Ministry of Science, Research and the Arts of the State of Baden-Württemberg