About

Daniel Donnelly

Daniel Donnelly portrait

About

I’m a PhD student advised by Sahar Abdelnabi at the Max Planck Institute for Intelligent Systems and ELLIS Institute Tübingen. My work focuses on AI safety, with interests in model personas, generalisation, chain-of-thought monitoring, long-context reasoning, and multi-LLM agent interactions. My current project focuses on evaluation awareness. If any of these overlap with your work, feel free to reach out.


Education