Added to make sure that I’m fulfilling my responsibilities (see job description).
Recent Updates Page 2
Two analyses
Made a calendar of predicted AI alignment events
Response to a comment on a project idea
Ten project ideas up for votes
Posted five each on LessWrong and the MIRIxDiscord.
Comment on a comment on ‘Techniques for optimizing worst-case performance’
Pointing out the possible cause of a misunderstanding. Posted on LessWrong.
Comment on a comment on ‘Learning with catastrophes’
Pointing out that the article already addressed the issue of bad outcomes that the agent can’t be held responsible for. Posted on LessWrong.
