Show notes
Worried about AGI running amok in the near future? John Wentworth thinks we can align AI. In 10-15 years. With greater than 50/50 probability. And he has a plan!We discuss The Plan, its merits, and how it has progressed over the past year.Primary Sources:The PlanThe Plan – 2022 UpdateAlso discussed:The Basic Foundations for Agent Models sequenceThe Telephone TheoremThe “Minimal Latents” Approach to Natural AbstractionsHelp With The Plan, Get The Skills, Save The World:Read The Embedded Agency SequenceJoin SERI MATS! (see also SERI MATS tag on LessWrong)Apply for funding from The Long-Term Future Fund56:05 – Guild of the Rose UpdateWe now partner with The Guild of the Rose, check them out.Hey look, we have a discord! What could possibly go wrong?Our Patreon page–your support is most rational, and totally effective. (also merch)Rationality: From AI to Zombies, The PodcastLessWrong Sequence Posts Discussed in this Episode:Expecting BeautyIs Reality Ugly?Next Episode’s Sequence Posts:Beautiful ProbabilityTrust in Math