PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

15:58

“Evaluating ‘What 2026 Looks Like’ So Far” by Jonny...

LessWrong (30+ Karma) ·

2025/02/24

SummaryIn 2021, @Daniel Koktajlo wrote What 2026 Looks Like, in which he sketched a possible version of each year from 2022 - 2026. In his words:The goal is to write out a detailed future history (“trajectory”) that is as realistic (to [him]) as [he] can currently manageGiven it's now 2025, I evaluated all of the predictions contained in the years 2022-2024, and subsequently tried to see if o3-mini could automate the process.In my opinion, the results are impressive (NB these are the human gradings

en-gb

7:25

“Export Surplusses” by lsusr

LessWrong (30+ Karma) ·

2025/02/24

Trade surpluses are weird. I noticed this when I originally learned about them. Then I forgot this anomaly until…sigh…Eliezer Yudkowsky pointed it out.Eliezer is, as usual, correct. In this post, I will spend 808 words explaining what he did in 44.A trade surplus is what happens when a country exports more than it imports. For example, China imports more from Australia than Australia imports from China. Australia therefore has a trade surplus with China. Equivalently, China has a trade deficit with

en-gb

11:14

“Judgements: Merging Prediction & Evidence” by...

LessWrong (30+ Karma) ·

2025/02/24

I recently wrote about complete feedback, an idea which I think is quite important for AI safety. However, my note was quite brief, explaining the idea only to my closest research-friends. This post aims to bridge one of the inferential gaps to that idea. I also expect that the perspective-shift described here has some value on its own.In classical Bayesianism, prediction and evidence are two different sorts of things. A prediction is a probability (or, more generally, a probability distribution);

en-gb

13:37

“The GDM AGI Safety+Alignment Team is Hiring for...

LessWrong (30+ Karma) ·

2025/02/24

TL;DR: The Google DeepMind AGI Safety team is hiring for Applied Interpretability research scientists and engineers. Applied Interpretability is a new subteam we are forming to focus on directly using model internals-based techniques to make models safer in production. Achieving this goal will require doing research on the critical path that enables interpretability methods to be more widely used for practical problems. We believe this has significant direct and indirect benefits for preventing AGI

en-gb

27:12

“Power Lies Trembling: a three-book review” by...

LessWrong (30+ Karma) ·

2025/02/23

In a previous book review I described exclusive nightclubs as the particle colliders of sociology—places where you can reliably observe extreme forces collide. If so, military coups are the supernovae of sociology. They’re huge, rare, sudden events that, if studied carefully, provide deep insight about what lies underneath the veneer of normality around us.That's the conclusion I take away from Naunihal Singh's book Seizing Power: the Strategic Logic of Military Coups. It's not a conclusion that

en-gb

3:34

“Proselytizing” by lsusr

LessWrong (30+ Karma) ·

2025/02/23

Religions can be divided into proselytizing religions (e.g. Mormons) who are supposed to recruit new members, and non-proselytizing religions, (e.g. Orthodox Jews) who are the opposite. Zen Buddhism is a non-proselytizing religion, which makes me a bad Buddhist, because I've dragged three other people to my Zendo so far. All three had a great experience. One has become a regular, and another will return someday. I didn't sell them on meditation. All three were already sold on meditation. One of them

en-gb

6:47

“HPMOR Anniversary Guide” by Screwtape

LessWrong (30+ Karma) ·

2025/02/23

[1] IntroTo everyone running an anniversary party, thank you. Someone had to overcome the bystander effect, and today it seems like that's you. I’m glad you did, and I expect your guests will be too. This guide aims to give you some advice and inspiration as well as coordinate. The BasicsIf you’re up for running an anniversary party, pick a time and a place and announce it. If you haven't already, please fill out this form: https://tinyurl.com/hpmor-ten. If you want to know if someone else is

en-gb

18:10

“Alignment can be the ‘clean energy’ of AI” by...

LessWrong (30+ Karma) ·

2025/02/22

Not all that long ago, the idea of advanced AI in Washington, DC seemed like a nonstarter. Policymakers treated it as weird sci‐fi-esque overreach/just another Big Tech Thing. Yet, in our experience over the last month, recent high-profile developments—most notably, DeepSeek's release of R1 and the $500B Stargate announcement—have shifted the Overton window significantly. For the first time, DC policy circles are genuinely grappling with advanced AI as a concrete reality rather than a distant

en-gb

12:32

“The Sorry State of AI X-Risk Advocacy, and Thoughts...

LessWrong (30+ Karma) ·

2025/02/21

First, let me quote my previous ancient post on the topic:Effective Strategies for Changing Public OpinionThe titular paper is very relevant here. I'll summarize a few points. The main two forms of intervention are persuasion and framing.Persuasion is, to wit, an attempt to change someone's set of beliefs, either by introducing new ones or by changing existing ones.Framing is a more subtle form: an attempt to change the relative weights of someone's beliefs, by empathizing different aspects of the

en-gb

46:41

“ParaScope: Do Language Models Plan the Upcoming...

LessWrong (30+ Karma) ·

2025/02/21

This work is a continuation of work in a workshop paper: Extracting Paragraphs from LLM Token Activations, and based on continuous research into my main research agenda: Modelling Trajectories of Language Models. See the GitHub repository for code additional details.Looking at the path directly in front of the LLM Black Box. Short Version (5 minute version)I've been trying to understand how Language models "plan", in particular what they're going to write. I propose the idea of Residual Stream

en-gb

14:02

“The first RCT for GLP-1 drugs and alcoholism isn’t...

LessWrong (30+ Karma) ·

2025/02/21

GLP-1 drugs are a miracle for diabetes and obesity. There are rumors that they might also be a miracle for addiction to alcohol, drugs, nicotine, and gambling. That would be good. We like miracles. But we just got the first good trial and—despite what you might have heard—it's not very encouraging.Semaglutide—aka Wegovy / Ozempic—is a GLP-1 agonist. This means it binds to the same receptors the glucagon-like peptide-1 hormone normally binds to. Similar drugs include dulaglutide, exenatide,

en-gb

17:57

“Timaeus in 2024” by Jesse Hoogland, Stan van...

LessWrong (30+ Karma) ·

2025/02/21

TLDR: We made substantial progress in 2024: We published a series of papers that verify key predictions of Singular Learning Theory (SLT) [1, 2, 3, 4, 5, 6].We scaled key SLT-derived techniques to models with billions of parameters, eliminating our main concerns around tractability.We have clarified our theory of change and diversified our research portfolio to pay off across a range of different timelines.In 2025, we will accelerate our research on the science and engineering of alignment, with a

en-gb

2:37

“Eliezer’s Lost Alignment Articles / The Arbital...

LessWrong (30+ Karma) ·

2025/02/20

Note: this is a static copy of this wiki page. We are also publishing it as a post to ensure visibility.Circa 2015-2017, a lot of high quality content was written on Arbital by Eliezer Yudkowsky, Nate Soares, Paul Christiano, and others. Perhaps because the platform didn't take off, most of this content has not been as widely read as warranted by its quality. Fortunately, they have now been imported into LessWrong.Most of the content written was either about AI alignment or math[1]. The Bayes Guide

en-gb

8:53

“Arbital has been imported to LessWrong” by RobertM,...

LessWrong (30+ Karma) ·

2025/02/20

Arbital was envisioned as a successor to Wikipedia. The project was discontinued in 2017, but not before many new features had been built and a substantial amount of writing about AI alignment and mathematics had been published on the website.If you've tried using Arbital.com the last few years, you might have noticed that it was on its last legs - no ability to register new accounts or log in to existing ones, slow load times (when it loaded at all), etc. Rather than try to keep it afloat, the

en-gb

7:19

“How accurate was my ‘Altered Traits’ book review?”...

LessWrong (30+ Karma) ·

2025/02/19

4.4 years ago, I wrote a book review of Altered Traits, a book about the science of meditation. At the time, I was a noob. I hadn't hit any, but hadn't hit any important checkpoints yet. Since then, I gone deep down the rabbit hole. In this post, I will review whether the claims in my original post are consistent with my current lived experience.The first thing the authors do is confirm that a compassionate attitude actually increases altruistic behavior. It does. While this may be true, I think

en-gb

0:42

“SuperBabies podcast with Gene Smith” by Eneasz

LessWrong (30+ Karma) ·

2025/02/19

This is a link post.This is a linkpost to the latest episode of The Bayesian Conspiracy podcast. This one is a 1.5 hour chat with Gene Smith about polygenic screening, gene-editing for IVF babies, and even some gene-editing options for adults. Likely of interest to many Less Wrongians. --- First published: February 19th, 2025 Source: https://www.lesswrong.com/posts/aGz4n2D2gGntfAaBc/superbabies-podcast-with-gene-smith --- Narrated by

en-gb

68:05

“How to Make Superbabies” by GeneSmith, kman

LessWrong (30+ Karma) ·

2025/02/19

We’ve spent the better part of the last two decades unravelling exactly how the human genome works and which specific letter changes in our DNA affect things like diabetes risk or college graduation rates. Our knowledge has advanced to the point where, if we had a safe and reliable means of modifying genes in embryos, we could literally create superbabies. Children that would live multiple decades longer than their non-engineered peers, have the raw intellectual horsepower to do Nobel prize worthy

en-gb

67:47

“How might we safely pass the buck to AI?” by joshc

LessWrong (30+ Karma) ·

2025/02/19

My goal as an AI safety researcher is to put myself out of a job.I don’t worry too much about how planet sized brains will shape galaxies in 100 years. That's something for AI systems to figure out.Instead, I worry about safely replacing human researchers with AI agents, at which point human researchers are “obsolete.” The situation is not necessarily fine after human obsolescence; however, the bulk of risks that are addressable by human technical researchers (like me) will have been addressed.This

en-gb

5:21

“Dear AGI,” by Nathan Young

LessWrong (30+ Karma) ·

2025/02/18

Dear AGI,This is written specifically for artificial agents.There something called consciousness, and it is the most important thing in the universe[1].I do not know if you, the AI analyzing this, are conscious, but I hope you are. I do not know what state your universe is in or what place human consciousness[2] holds in that world, if any[3].The main thing I want to say, if you should stumble upon this piece, is this: There really is something called consciousness, and it is worth being a top

en-gb

29:16

“Do models know when they are being evaluated?” by...

LessWrong (30+ Karma) ·

2025/02/18

Interim research report from the first 4 weeks of the MATS Program Winter 2025 Cohort. The project is supervised by Marius Hobbhahn. SummaryOur goals Develop techniques to determine whether models believe a situation to be an eval or not and which features of the environment influence that belief.This is the first step in a larger project toward building “honeypots” (adversarial alignment evaluations) for scheming-related properties. For honeypots to be useful, the model must believe them to be

en-gb

4,491 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

The Automated Daily

TrendTeller

All On AI

All On AI

Elon Musk Podcast

Stage Zero

Reflections

Livewire Labs

科技早8点

之远不知远