Inspired by Eugene Yan’s paper club, we started one for AI safety. We meet when it works. Yes, the name’s a joke. No, Skynet’s not coming for your office supplies. But yes, AI risks are real.
May
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
Events
You have 0 events pending approval by the calendar admin.
They will show up on the schedule once approved
Paper Club #012: "Pitfalls of Evidence-Based AI Policy" by Casper, Krueger, and Hadfield-Menell (2025)
By Lenz Dagohoy
Zoom
Paper Club #013: "Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models" by Lehdonvirta et al. (2024)
By Lenz Dagohoy
Zoom
Paper Club #014: "Superintelligence Strategy" by Hendrycks, Schmidt, and Wang (2025)
