Hello, I’m Jan Wehner. I research AI Governance, currently at GovAI as a Winter Fellow under Alan Chan. I previoulsy done research on AI Safety and Interpretability at CISPA Helmholtz Center for Information supervised by Prof. Mario Fritz and Prof. David Krueger. I’ve worked on Representation Engineering, Harmful fine-tuning attacks and Inverse Reinforcement Learning.

I want to make the future better by influencing the developing of AI. Also I do some writing on my blog.

Please don’t hesitate to reach out ot me at janwehner1(at)t-online.de!