Artificial Agency Speaker Series

Events

• AI Agents and Morality: Towards Norm-Aligned Design Choices (Esther Jaromitski, Queen Mary University) 2025-11-29
• The AI Agent Index: What Deployments Reveal About Safety and Autonomy (Leon Staufer, MATS & University of Cambridge) 2025-11-19
• Anti-Scheming: how would we train a model not to scheme? (Bronson Schoen and Marius Hobbhahn, Apollo Research) 2025-11-08
• Evaluating harmful agents: learnings from AgentHarm and follow-up work (Mateusz Dziemian, Gray Swan AI) 2025-11-01
• Are we testing the right things in multi-agent AI? (Ruchira Dhar, University of Copenhagen) 2025-10-25
• Assessing Harm in AI Agents: What Questionnaires Miss (Max Hellrigel-Holderbaum, FAU Erlangen-Nürnberg) 2025-10-18