AI Safety Evals Paper Reading Group - Papers I’m Reading Breakouts (special)
It’s your turn to tell each other the paper(s) you’re reading (no stress)!
Join us for a special session AI Safety Reading Group: Paper Breakout Discussions
Bring 1-2 papers you've read recently. You’re not presenting, just saying what you thought of it. You’ll get to connect with a few other reading group members better too!
They can be any AI Safety paper, optimally from the last 3-6 months.
Breakouts: 2 rounds of 20-min (~6 people): quick intros, then swap papers you found interesting recently.
Share Papers we found: Each group logs its papers to a shared list: AI Safety Area, Key Results, Novelty, Significance, Limitations. Collective intelligence in action!
Optionally: Stay an extra 10-15 min for quick call-outs of the top papers from all groups.
Next week we’ll go back to our regular format where someone will present for up to 30 minutes followed by group discussion.
☑️ RSVP here on Luma to join
Also: AI Safety Evals Paper Reading Group website, sign up to present, or contact us at evalsreadinggroup@gmail.com with questions. Everyone is welcome!
Host: Andreas Turanski, Mark Keavney
Sponsored by: BlueDot Impact