This is [besed on] a lightly edited transcript of a chatroom conversation between Scott Alexander and Eliezer Yudkowsky last year, following up on the Late 2021 MIRI Conversations. Questions discussed include "How hard is it to get the right goals into AGI systems?" and "In what contexts do AI systems exhibit 'consequentialism'?".

https://www.alignmentforum.org/posts/rwkkcgSpnAyE8oNo3/alexander-and-yudkowsky-on-agi-goals