The Bayesian Conspiracy

Duncan Sabien on dynamics [can] arise if you have people nudging in that direction (also thanks to Liam from 2 Rash 2 Unadvised podcast for intro)

My Model Of EA Burnout

We discuss Microsoft’s new Bing search chatbot – Sydney. It received a wave of media coverage due to erratic behavior, before being neutered by Microsoft. A dive into its behavior, human responses, and implications. Links The Birth and Death of Sydney “Sydney Is Now Immortal” Zvi’s Round-up Gwern’s comment on Bing/Sydney Astral Codex Ten post on Janus Simulators Bankless crypto podcast – We’re All Gonna Die with Eliezer Yudkowsky Eneasz’s Change.org Petition Sydney-based erotica Other Links The Parable of the Dagger and The Parable of the Dagger. One of these is Eneasz, the other one is a voice-matching AI. The Uncanny Vulva Follow Moridinamael on Twitter email the show: bayesianconspiracypodcast@gmail.com Which AI do you prefer: or (Spoiler: they’re the same picture) 0:00:53 – Steven’s Media Corner 0:01:48 – Chat with Eneasz IRL 0:02:31 – Sydney/Bing AI 01:31:09 – Guild of the Rose Update 01:33:58 – Thank the Patron We 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 Podcast LessWrong Sequence Posts Discussed in this Episode: still not Next Sequence Posts: The Allais Paradox Zut Allais!

We discuss Zvi’s How to Bounded Distrust with Wesley Fenza. Wes is from The Mind Killer! Other links: Bounded Distrust On Bounded Distrust The Media Very Rarely Lies + followup + 2nd followup People Will Sometimes Just Lie About You Matt Yglesia on Why You Can’t Trust The Media Discovery in lawsuit case shows FOX News hosts didn’t believe their own narrative NYT leadership decided tech will be covered negatively Conflict Theory of Bounded Distrust Eneasz did the dumb homework: MIT article on how the vaccine was delayed by a week to just after the election Nate Silver said it deserves looking into Zvi says of Topol “there was the time he was instrumental in sabotaging approval of the Covid vaccines so that it would happen after the November election.” 00:01 – How To Bounded Distrust 01:10:51 – Guild of the Rose Update 01:12:31 – Thank the Patron We 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 Podcast LessWrong Sequence Posts Discussed in this Episode: nope Next Episode’s Sequence Posts: The Allais Paradox Zut Allais!

In Defense of Chatbot Romance

We have some follow-up questions to Brian, including how to weigh utils, how moral claims to an area can be adjudicated, crime, use of home ownership as an investment as government policy, eviction law, and more! For the full episode, subscribe at Patreon CA YIMBY main page and support pages here

We discuss the YIMBY movement in California, and how Brian Hanlon & co. got real legislative change happening. Primary Links CA YIMBY Contact Brian – Brian@CAYIMBY.org Great article on SB827 including interview with Brian The Welcoming Neighbor Network Other Links George Carlin on NIMBY CARLA is now CalHDF SF BARF Black-Eyes put on a hell of a punk show… and they just reunited to put on three shows this coming April TBC episode on Getting Lucky TBC episode on Georgist Land Value Taxes A COVIDy blog post on getting Paxlovid in the US Clearer Thinking on Importance Hacking 00:01 – CA YIMBY 01:01:16 – Possible to Slow AI via Legislation? 01:08:57 – Guild of the Rose Update 01:09:49 – LW posts 01:43:09 – Thank the Patron We 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 Podcast LessWrong Sequence Posts Discussed in this Episode: Beautiful Probability Trust in Math Next Episode’s Sequence Posts: The Allais Paradox Zut Allais!

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 Plan The Plan – 2022 Update Also discussed: The Basic Foundations for Agent Models sequence The Telephone Theorem The “Minimal Latents” Approach to Natural Abstractions Help With The Plan, Get The Skills, Save The World: Read The Embedded Agency Sequence Join SERI MATS! (see also SERI MATS tag on LessWrong) Apply for funding from The Long-Term Future Fund 56:05 – Guild of the Rose Update 57:36 – Feedback 58:20 – LW posts 1:19:09 – Thank the Patron We 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 Podcast LessWrong Sequence Posts Discussed in this Episode: Expecting Beauty Is Reality Ugly? Next Episode’s Sequence Posts: Beautiful Probability Trust in Math

We discuss Out To Get You by Zvi. A lot of clouds get yelled at. 2:55 – Main Topic: Getting Got 1:08:48 – LW posts 1:18:55 – Thank the Patron 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 Podcast LessWrong Sequence Posts Discussed in this Episode: 0 And 1 Are Not Probabilities Beautiful Math Next Episode’s Sequence Posts: Expecting Beauty Is Reality Ugly?

Matt Freeman gives a primer in how to uses Bayesian decision making in normal life, via decision trees. We also discuss utilitarianism, the Guild of the Rose, and recent AI advances. We are now in the early singularity. Guild of the Rose: Playlist of Decision Tree “lectures” Guild workshop page 1 Guild workshop page 2 Guild workshop page 3 Reflecting on the 2022 Guild of the Rose Workshops How to identify whether text is true or false directly from a model’s *unlabeled activations*. Zvi On the Diplomacy AI AI superpowers – can tell race via chest Xray. Can tell sex via retina scan (87%). 0:00:23 Practical Decision Trees 1:05:46 Utilitarian & Other Ethics considerations 1:31:01 Guild of the Rose info 1:39:02 Bayesian AI Corner 2:08:18 Should we have a Butlerian Jihad? 2:31:36 Thank the Patron! 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 Podcast LessWrong Sequence Posts Discussed in this Episode: Nope Next Episode’s Sequence Posts: (for real this time) 0 And 1 Are Not Probabilities Beautiful Math