Jonathan Erhardt

Jonathan Erhardt is a Research Fellow at the Department of Philosophy, University of Zurich, leading the SNSF Starting Grant-funded project "Propositional Interpretability in Artificial Intelligence." His interdisciplinary work bridges philosophical inquiry with artificial intelligence development to enhance transparency in AI decision-making systems.

Education:

• BPhil in Philosophy, University of Oxford (2012-2014)
• PhD in Law, University of Bern (2009-2013)

Research Interests:

Erhardt investigates foundational questions at the intersection of AI and philosophy of mind, focusing on how artificial systems represent propositional content and generate interpretable outputs. His work examines epistemological frameworks for explaining AI behavior while addressing ethical implications of opaque decision systems in high-stakes domains. Current research develops philosophical models to ground technical interpretability methods in cognitive science principles.

Scientific Awards:

• SNSF Starting Grant

As principal investigator of the SNSF Starting Grant project, Erhardt directs an independent research program exploring philosophical foundations of AI interpretability. No graduate student supervision is documented in available sources. His methodology combines conceptual analysis with technical AI validation to establish robust interpretability standards applicable across machine learning paradigms.

Professional Experience:

• Founder and Programmer, Twin Earth Games (2016-present)
• Philosophy Teacher, High School Thun (2016-2021)
• Research Associate and Project Lead, Giordano-Bruno Foundation Switzerland / Effective Altruism Foundation (2014-2016)