PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

10:17

“Aesthetic Preferences Can Cause Emergent...

LessWrong (30+ Karma) ·

2025/08/26

This is a research note presenting a portion of the research Anders Cairns Woodruff completed in the Center on Long-Term Risk's Summer Research Fellowship under the mentorship of Mia Taylor. The datasets can be found at https://huggingface.co/datasets/AndersWoodruff/AestheticEM TL;DR Unpopular aesthetic preferences cause emergent misalignment on multiple models. Ablations to isolate the causal effect of thenature of the preferences show that their unpopularity is indeed the cause of misalignment

en-gb

26:01

“Hidden Reasoning in LLMs: A Taxonomy” by Rauno Arike

LessWrong (30+ Karma) ·

2025/08/26

Summary When discussing the possibility that LLMs will cease to reason in transparent natural language with other AI safety researchers, we have sometimes noticed that we talk past each other: e.g., when discussing ‘neuralese reasoning’, some people have indefinitely long chains of recurrent activations in mind, while others think of an alien language in token-space. This post will propose terminology for distinguishing different types of hidden reasoning to create a shared language for such

en-gb

36:18

“A Comprehensive Guide to Running” by Declan Molony

LessWrong (30+ Karma) ·

2025/08/26

Just because you can run, it doesn't mean that you know how to do it properly. This systematic review showed that: 50% of runners experience an injury each year that prevents them from running for a period of time, and 25% of runners are injured at any given time. Running-related musculoskeletal injuries (RRMIs) are common among runners. These RRMIs are usually caused by the application of relatively small loads over many repetitive cycles. When your form is wrong, because running is a repetitive

en-gb

3:13

[Linkpost] “Breastfeeding and IQ: Effects shrink as...

LessWrong (30+ Karma) ·

2025/08/26

This is a link post. Socioeconomic status, parental education, and parental intelligence have strong effects on child IQ and are themselves correlated with breastfeeding practices. When studies ignore these confounders, they often find significant IQ increases in breastfed groups (5-8 points). As more confounders are accounted for, the gap typically shrinks to 2-3 points. Some relevant studies: Der, Batty & Deary, 2006: 5475 children, controlled for most relevant factors including maternal IQ →

en-gb

2:03

“New Paper on Reflective Oracles & Grain of Truth” by...

LessWrong (30+ Karma) ·

2025/08/26

This is a linkpost for https://www.arxiv.org/pdf/2508.16245 With Marcus Hutter, Jan Leike (@janleike), and Jessica Taylor (@jessicata) , I have revisited Leike et al.'s paper "A Formal Solution to the Grain of Truth Problem" (AFSGOTP) which studies games between reflective AIXI agents and... further formalized it. The result is "Limit-Computable Grains of Truth for Arbitrary Computable Extensive-Form (Un)Known Games" (LCGOTACEFUG) which perhaps could have been called "A Formal Formal Solution to

en-gb

26:08

“Neuroscience of human sexual attraction triggers (3...

LessWrong (30+ Karma) ·

2025/08/26

tl;dr There's a stereotype that male sexual attraction is triggered mainly by appearance, and female sexual attraction is triggered mainly by status.…Yes I know, this stereotype is grossly oversimplified, and is only valid on the margin, and really there's overlapping distributions, etc. etc. (+ even more caveats in §1.2 below). But it does have a kernel of truth.[1] Now, this post is not mainly about sex differences per se. What I actually care about is the more basic observation that

en-gb

5:27

“Before LLM Psychosis, There Was Yes-Man Psychosis”...

LessWrong (30+ Karma) ·

2025/08/25

A studio executive has no beliefs That's the way of a studio system We've bowed to every rear of all the studio chiefs And you can bet your ass we've kissed 'em Even the birds in the Hollywood hills Know the secret to our success It's those magical words that pay the bills Yes, yes, yes, and yes! “Don’t Say Yes Until I Finish Talking”, from SMASH So there's this thing where someone talks to a large language model (LLM), and the LLM agrees with all of their ideas, tells them they’re brilliant,

en-gb

47:45

“Arguments About AI Consciousness Seem Highly...

LessWrong (30+ Karma) ·

2025/08/25

I happily admit I am deeply confused about consciousness.I don’t feel confident I understand what it is, what causes it, which entities have it, what future entities might have it, to what extent it matters and why, or what we should do about these questions. This applies both in terms of finding the answers and what to do once we find them, including the implications for how worried we should be about building minds smarter and more capable than human minds. Some people respond to this

en-gb

5:31

“The Best Materials To Build Any Intuition” by Algon

LessWrong (30+ Karma) ·

2025/08/25

Many textbooks, tutorials or ... tapes leave out the ways people actually think about a subject, and leave you to fumble your way to your own picture. They don't even attempt to help you build intuitions. (Looking at you, Bourbaki.) This sucks. I love it when explanations try to tap into what I can touch, feel and see. Yes, you still have to put in work to understand why an idea's intuitive, but it leaves you much richer than when you started. I've occasionally found Luke's The Best Textbooks on

en-gb

5:20

“Kids and Cleaning” by jefftk

LessWrong (30+ Karma) ·

2025/08/25

Before having kids I thought teaching them to clean up would be similar to the rest of parenting: once they're physically able to do it you start practicing with them, and after a while they're independent and do it reliably. You invest time and effort up front, but it pays back reasonably quickly with benefits for both you and the kid. While we've (n=3) had good success in some areas ( street safety, microwave usage, walking to school, tooth brushing, ...), tidying has not been one of

en-gb

8:36

“Futility Illusions” by silentbob

LessWrong (30+ Karma) ·

2025/08/24

…or the it doesn’t make a difference anyway fallacy. Improving Productivity is Futile I once had a coaching call on some generic productivity topic along the lines of “I’m not getting done as much as I’d like to”. My hope was that we might identify ways for me to become more productive and get more done. The coach, however, very quickly narrowed in on figuring out what I typically work on in order to eliminate the least valuable things – also a good idea for sure, but this approach seemed a

en-gb

61:04

“Notes on cooperating with unaligned AI” by Lukas...

LessWrong (30+ Karma) ·

2025/08/24

These are some research notes on whether we could reduce AI takeover risk by cooperating with unaligned AIs. I think the best and most readable public writing on this topic is “Making deals with early schemers”, so if you haven't read that post, I recommend starting there. These notes were drafted before that post existed, and the content is significantly overlapping. Nevertheless, these notes do contain several points that aren’t in that post, and I think it could be helpful for people who are

en-gb

9:16

“Shorter Tokens Are More Likely” by Brendan Long

LessWrong (30+ Karma) ·

2025/08/24

I was thinking about LLM tokenization (as one does) and had a thought: We select the next output token for an LLM based on its likelihood, but shorter tokens are more likely. Why? Shorter common tokens are (correctly) learned to be higher-probability because they have the combined probability of any word they could complete. However, standard generation techniques will only consider a subset of probabilities and scale the largest probabilities. Both of these will take the highest probabilities and

en-gb

8:06

“DeepSeek v3.1 Is Not Having a Moment” by Zvi

LessWrong (30+ Karma) ·

2025/08/24

What if DeepSeek released a model claiming 66 on SWE and almost no one tried using it? Would it be any good? Would you be able to tell? Or would we get the shortest post of the year?Why We Haven’t Seen v4 or r2 Why are we settling for v3.1 and have yet to see DeepSeek release v4 or r2 yet? Eleanor Olcott and Zijing Wu: Chinese artificial intelligence company DeepSeek delayed the release of its new model after failing to train it using Huawei's chips, highlighting the limits of Beijing's push to

en-gb

8:50

“Yudkowsky on ‘Don’t use p(doom)’” by Raemon

LessWrong (30+ Karma) ·

2025/08/23

For awhile, I kinda assumed Eliezer had basically coined the concept of p(Doom). Then I was surprised one day to hear him complaining about it being an antipattern he specifically thought was unhelpful and wished people would stop. He noted: "If you want to trade statements that will actually be informative about how you think things work, I'd suggest, "What is the minimum necessary and sufficient policy that you think would prevent extinction?" Complete text of the corresponding X Thread: I spent

en-gb

51:48

“Banning Said Achmiz (and broader thoughts on...

LessWrong (30+ Karma) ·

2025/08/22

It's been roughly 7 years since the LessWrong user-base voted on whether it's time to close down shop and become an archive, or to move towards the LessWrong 2.0 platform, with me as head-admin. For roughly equally long have I spent around one hundred hours almost every year trying to get Said Achmiz to understand and learn how to become a good LessWrong commenter by my lights.[1] Today I am declaring defeat on that goal and am giving him a 3 year ban. What follows is an explanation of the models

en-gb

19:50

“(∃ Stochastic Natural Latent) Implies (∃...

LessWrong (30+ Karma) ·

2025/08/22

Audio note: this article contains 212 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Our posts on natural latents have involved two distinct definitions, which we call "stochastic" and "deterministic" natural latents. We conjectured that, whenever there exists a stochastic natural latent (to within some approximation), there also exists a deterministic natural latent (to within a comparable approximation). Four

en-gb

16:24

“Mustafa Suleyman’s ‘Seemingly Conscious AI’ Post” by...

LessWrong (30+ Karma) ·

2025/08/22

Recently, the CEO of Microsoft AI posted an article on his blog called "Seemingly Conscious AI is Coming". Suleyman's post involves both "is" and "ought" claims, first describing the reality of the situation as he sees it and then prescribing a set of actions which he believes the industry at large should take. I detail those below, and conclude with some of my takeaways. Suleyman's "Is" Claims on Consciousness Defining Consciousness Suleyman acknowledges that consciousness as a concept is ill

en-gb

26:02

“An Introduction to Credal Sets and Infra-Bayes...

LessWrong (30+ Karma) ·

2025/08/22

Audio note: this article contains 247 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Introduction Credal sets, a special case of infradistributions[1] in infra-Bayesianism and classical objects in imprecise probability theory, provide a means of describing uncertainty without assigning exact probabilities to events as in Bayesianism. This is significant because as argued in the introduction to this sequence,

en-gb

14:44

“When Money Becomes Power” by Gabriel Alfour

LessWrong (30+ Karma) ·

2025/08/22

I know many people in the libertarian right quadrant of the political compass: progress studies people, economists, techno-optimists, anarcho-capitalists, proper libertarians, etc. They usually ignore why people may oppose rich people getting richer on principle. This essay is an explanation for them, focusing on how wealth concentration is an especially pernicious form of concentration of power. The Starting Point: Free and Equal It is bad for a stranger to have power over us. Foremost, it is

en-gb

4,486 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Double Tap

Double Tap Productions Inc.

Primary Technology

Stephen Robles and Jason Aten

Techlandia

Technology Association of Oregon

Eye On A.I.

Craig S. Smith

The Milk Road Show

The Milk Road Show