Technical Agendas Reading Group

Technical Agendas Reading Group

Express your interest by January 22nd

This group will meet weekly to read and discuss the key papers from a number of different technical AI safety research agendas (e.g. control, GSAI). The goal is to understand the core assumptions underpinning current approaches and to understand the cases when a particular agenda no longer makes sense.

The sessions will likely run for 2hrs at a time. We’ll run a poll to determine exact time/location will be coordinated once the group has been formed. We’ll provide snacks!

We expect the members of this group to have some background technical AI safety knowledge and an interest in working in the field.