Reading Group & Discussion: Cooperative AI

​This week's reading group will be focused on Cooperative AI, and we'll have a guest facilitator - Claude Formanek!

​We'll be discussing the following resources:

• ​Intro to Cooperative AI Video: https://www.youtube.com/watch?v=ZUi-kP_X2K4

• ​Section 2.6: Multi-Agent Safety Is Not Assured by Single-Agent Safety (in LLMs): https://arxiv.org/pdf/2404.09932

• ​Open Problems in Cooperative AI: https://arxiv.org/pdf/2012.08630

​Note:

• ​​​Please review the resources before attending the reading to make the best use of the discussion.

• ​​​Please RSVP on the Luma event

​​​We're looking forward to seeing you there!