AI Safety Reading Group
We're excited to announce that Safe AI Lausanne will be hosting a bi-weekly reading group focused on AI Safety.
When: Every other Wednesday, starting October 8th, 2024, from 18:30 to 20:00
The paper we will talk about in the following session : Stress Testing Deliberative Alignment for Anti-Scheming Training('25)
This reading group is open to everyone interested in AI Safety, though having some background in modern AI concepts will help you get the most out of our discussions. Whether you're just starting to explore AI Safety or already have experience in the field, we welcome participants from all backgrounds!
Each session, we'll dive into important papers, discuss key concepts, and explore the latest developments in making AI systems safer and more aligned with human values.
Please fill out this form to participate in the next reading group!