F2025 - Technical Paper Reading Group Week 1
UBC AI Safety Technical Paper Reading Group
UBC AI Safety is launching a biweekly technical paper reading group focused on cutting-edge AI safety research, beginning September 24th.
Sessions will engage participants with recent papers across topics including mechanistic interpretability, AI control, scalable oversight, capability evaluation, and failure mode identification. The group emphasizes critical analysis and discussion and seeks to help participants develop skills in evaluating technical research.
Session 1: Research Landscape & Group Vision
Our first meeting will explore the current landscape of technical AI safety research through interactive activities. We'll also collectively shape the direction and format of future sessions to best serve everyone's interests and goals.
Who Should Attend:
Meetings are open to anyone interested in technical AI safety research. While no prior experience is required, participants with working knowledge of AI Safety and machine learning concepts will get the most out of discussions. If you're unsure whether you have sufficient background, check out this preparation document which gives resources on topics you should be familiar with for maximum engagement with the material.