The summer school featured an impressive lineup of speakers from prestigious institutions such as Carnegie Mellon University, Massachusetts Institute of Technology (MIT), Google DeepMind, and the University of Cambridge. Their presentations covered a broad range of topics, including Mechanistic Interpretability (MechInterp), Reinforcement Learning from Human Feedback (RHFL), and Adversarial Robustness. These discussions were supplemented by interactive workshops, providing Haadia and other attendees with opportunities to engage deeply with the experts and explore their own research interests.

For Haadia, whose research focuses on Explainable AI (xAI), the summer school was particularly relevant. Although xAI is not exclusively about alignment, it plays a crucial role in developing AI systems that are transparent and trustworthy. The emphasis on interpretability and human feedback at the summer school highlighted the importance of making AI systems understandable and reliable, aligning perfectly with Haadia’s research objectives and the broader goals of AI safety.

© DAAD/Nathan Dreessen

Haadia Amjad in conversation

Haadia Amjad is a member of the Explainable Artificial Intelligence Group of the Chair of Fundamentals of Engineering (XAI-GE). This group is committed to advancing xAI methods and applying them across various domains, including surgical skill assessment, autonomous driving, and mechanical anomaly detection. Under the supervision of Professor Ronald Tetzlaff, the group collaborates with leading institutions to ensure that their research remains at the cutting edge. Haadia’s participation in the summer school underscores the group's dedication to integrating the latest research into practical solutions that enhance the transparency and effectiveness of AI systems.