On Friday 6th November Neel Nanda is returning to Oxford to give a talk. Neel leads the mechanistic interpretability team at Google DeepMind and will give an overview of interpretability and how it can and cannot help AI safety.
No technical background is needed to attend, and after the talk, you'll have the chance to chat more with Neel and Oxford AI Safety Initiative (OAISI) members over pizza. The talk will be hosted in the L1 Lecture Theatre of the Mathematical Institute, beginning at 19:30.
Last year, OAISI welcomed ~270 people to hear Neel give a deep dive into interpretability and frontier AI research. Those of you who attended will remember it filling the entire lecture theatre plus an overflow room. So, if you missed it, this is your chance.
Location: L1 Lecture Theatre, Mathematical Institute, University of Oxford
Time: Friday 6th November, 19:30–21:30
RSVP here (https://luma.com/50cw1fh1?tk=wK35DH)
