Podcast Lesswrong

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Announcing Encultured AI: Building a Video Game, published by Andrew Critch on August 18, 2022 on LessWrong.Also available on the EA Forum.Preceded By: Encultured AI…

https://www.lesswrong.com/posts/CjFZeDD6iCnNubDoS/humans-provide-an-untapped-wealth-of-evidence-about#fnref7a5ti4623qb Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. TL;DR: To even consciously consider an alignment research direction, you should have evidence to locate it as a promising lead. As best I can te…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Human Mimicry Mainly Works When We’re Already Close, published by johnswentworth on August 17, 2022 on LessWrong.What if we just simulate a bunch of alignment resear…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The longest training run, published by Jsevillamol on August 17, 2022 on LessWrong.In short: Training runs of large Machine Learning systems are likely to last less …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Autonomy as taking responsibility for reference maintenance, published by Ramana Kumar on August 17, 2022 on LessWrong.I think semantics – specifically, maintaining …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: My thoughts on direct work (and joining LessWrong), published by RobertM on August 16, 2022 on LessWrong.Epistemic status: mostly a description of my personal timeli…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Against population ethics, published by jasoncrawford on August 16, 2022 on LessWrong.The following is an excerpt from some comments I wrote to Will MacAskill about …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Brain-like AGI project "aintelope", published by Gunnar Zarncke on August 14, 2022 on LessWrong.Steven Byrnes called for a brain-like AGI research agenda, and three …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: What's General-Purpose Search, And Why Might We Expect To See It In Trained ML Systems?, published by johnswentworth on August 15, 2022 on LessWrong.Ben Pace has an …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: I’m mildly skeptical that blindness prevents schizophrenia, published by Steven Byrnes on August 15, 2022 on LessWrong.(Low confidence, written in a hurry.)I was (ra…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Extreme Security, published by lc on August 15, 2022 on LessWrong.What makes "password" a bad password?You might say that it's because everybody else is already usin…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Cultivating Valiance, published by Shos Tekofsky on August 13, 2022 on LessWrong.When I discovered existential risk from AGI I was surprised to learn most people fin…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The Parable of the Boy Who Cried 5% Chance of Wolf, published by KatWoods on August 15, 2022 on LessWrong.Epistemic status: a parable making a moderately strong clai…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Gradient descent doesn't select for inner search, published by Ivan Vendrov on August 13, 2022 on LessWrong.TL;DR: Gradient descent won't select for inner search pro…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Credence Calibration Icebreaker Game, published by Ruby on August 14, 2022 on LessWrong.The Aussie mega-meetup took place this past weekend. For it, a new kind of ic…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Appendix: Building a Bugs List prompts, published by CFAR!Duncan on August 13, 2022 on LessWrong.Prompt 0:Think about the way computer programmers talk about “bugs” …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: All the posts I will never write, published by Self-Embedded Agent on August 14, 2022 on LessWrong.This post has been written for the first Refine blog post day, at …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: How to bet against civilizational adequacy?, published by Wei Dai on August 12, 2022 on LessWrong.Coal prices are at historical highs (2x to 4x normal prices dependi…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: DeepMind alignment team opinions on AGI ruin arguments, published by Vika on August 12, 2022 on LessWrong.We had some discussions of the AGI ruin arguments within th…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Introducing Pastcasting: A tool for forecasting practice, published by Sage Future on August 11, 2022 on LessWrong.TL;DR: Visit pastcasting.com to forecast on alread…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: How and why to turn everything into audio, published by KatWoods on August 11, 2022 on LessWrong.If you love podcasts and audiobooks and find yourself occasionally f…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Shard Theory: An Overview, published by David Udell on August 11, 2022 on LessWrong.Generated as part of SERI MATS, Team Shard's research, under John Wentworth.Many …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: How To Go From Interpretability To Alignment: Just Retarget The Search, published by johnswentworth on August 10, 2022 on LessWrong.When people talk about prosaic al…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Proposal: Consider not using distance-direction-dimension words in abstract discussions, published by moridinamael on August 9, 2022 on LessWrong.Epistemic Status: L…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Team Shard Status Report, published by David Udell on August 9, 2022 on LessWrong.Team Shard is a nebulous alignment research collective, on paper siloed under John …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: How (not) to choose a research project, published by Garrett Baker on August 9, 2022 on LessWrong.Background(specific information will be sparse here. This is meant …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Interpretability/Tool-ness/Alignment/Corrigibility are not Composable, published by johnswentworth on August 8, 2022 on LessWrong.InterpretabilityI have a decent und…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Steganography in Chain of Thought Reasoning, published by A Ray on August 8, 2022 on LessWrong.Here I give a possible phenomenon of steganography in chain of thought…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The lessons of Xanadu, published by jasoncrawford on August 7, 2022 on LessWrong.One of my all-time favorite articles is “The Curse of Xanadu,” by Gary Wolf, which r…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Why I Am Skeptical of AI Regulation as an X-Risk Mitigation Strategy, published by A Ray on August 6, 2022 on LessWrong.Epistemic Signpost: I'm not an expert in poli…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Six weeks doesn’t make a habit, published by lynettebye on August 6, 2022 on LessWrong.I occasionally get asked some version of “How long do I need to practice my ha…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Paper reading as a Cargo Cult, published by jem-mosig on August 7, 2022 on LessWrong.I have come across various people (including my past self) who meet up regularly…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Jack Clark on the realities of AI policy, published by Kaj Sotala on August 7, 2022 on LessWrong.Some choice picks:The real danger in Western AI policy isn't that AI…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Most Ivy-smart students aren't at Ivy-tier schools, published by Aaron Bergman on August 7, 2022 on LessWrong.[I posted this on the EA Forum as well, and may as well…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: «Boundaries», Part 2: trends in EA's handling of boundaries, published by Andrew Critch on August 6, 2022 on LessWrong.This is Part 2 of my «Boundaries» Sequence on …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Post-mortem?, published by gwern on August 5, 2022 on LessWrong.As Covid is for the most part over and tests have not been in short supply for a very long time now, …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The Falling Drill, published by Screwtape on August 5, 2022 on LessWrong.Summary: The Falling Drill is intended to practice being wrong in a comfortable practice env…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Fiber arts, mysterious dodecahedrons, and waiting on “Eureka!”, published by eukaryote on August 4, 2022 on LessWrong.Part 1: The anomalyThis story starts, as many s…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Covid 8/4/22: Rebound, published by Zvi on August 4, 2022 on LessWrong.I’ll be at Future Forum over the weekend. If you’re here, come and say hello. I don’t plan on …

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: What do ML researchers think about AI in 2022?, published by KatjaGrace on August 4, 2022 on LessWrong.Katja Grace, Aug 4 2022AI Impacts just finished collecting dat…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Clapping Lower, published by jefftk on August 4, 2022 on LessWrong.Clapping is normally relatively high pitch:(mp3)I find clapping annoyingly high, so I usually clap…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Announcing Squiggle: Early Access, published by ozziegooen on August 3, 2022 on LessWrong.Update: We've announced a $1,000 prize for early experimentation with Squig…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: High Reliability Orgs, and AI Companies, published by Raemon on August 4, 2022 on LessWrong.Epistemic Effort: Rough notes from a shallow dive. Looked into this for a…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Againstness, published by CFAR!Duncan on August 2, 2022 on LessWrong.Author's note: Sometimes, when a CFAR instructor left the org, there would not be another instru…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Turbocharging, published by CFAR!Duncan on August 2, 2022 on LessWrong.Author's note: Sometimes, when a CFAR instructor left the org, there would not be another inst…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Flash Classes: Polaris, Seeking PCK, and Five-Second Versions, published by CFAR!Duncan on August 1, 2022 on LessWrong.Author's note: During CFAR's 4.5d workshops, c…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Meditation course claims 65% enlightenment rate: my review, published by KatWoods on August 1, 2022 on LessWrong.TL;DRI eliminated my impostor syndrome and dramatica…

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Perverse Independence Incentives, published by jefftk on July 31, 2022 on LessWrong.In writing about parenting, I don't write enough about what didn't work: this mig…

https://www.lesswrong.com/posts/DdDt5NXkfuxAnAvGJ/changing-the-world-through-slack-and-hobbies Introduction In EA orthodoxy, if you're really serious about EA, the three alternatives that people most often seem to talk about are (1) “direct work” in a job that furthers a very important cause; (2) “earning to give”; (3) earning “career capital” that…