BLISS AI Speaker Series #36: Towards Automated Interpretability for AI Safety - Fazl Barez

We are thrilled to feature Fazl Barez, a Senior Research Fellow at the University of Oxford, who will present on "Towards Automated Interpretability for AI Safety" for about 45 minutes.

🎉 After the talk, don’t miss the chance to network with fellow AI enthusiasts, exchange ideas, and dive into discussions while enjoying free drinks and pizza!
🔒 Please arrive early as doors will close by 7:15 PM. Make sure to RSVP on Luma to secure your entry.

Who is this event for?

This event welcomes everyone with an interest in cutting-edge AI research, especially tailored for students, PhD candidates, academic researchers, and industry professionals focusing on machine learning.

Abstract & Bio

TBA

We are BLISS e.V., an AI organization in Berlin dedicated to connecting individuals who share a passion for the field of machine learning. This summer 2026, we will once again host an exciting speaker series featuring exceptional researchers from Cohere, ETH Zürich, University of Oxford, HuggingFace, and Stanford University.

🌐 Website
📺 YouTube Channel

Disclaimer: By attending this event, you consent to being photographed.