PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

3:34

“France is ready to stand alone” by Lucie Philippon

LessWrong (30+ Karma) ·

2025/11/11

First part of a series of article on French AI Policy that I’m currently writing as part of the Inkhaven Residency. For three centuries, France has stood among the great powers of the world, and there it wants to stay. Now, far from the heyday of La Belle Époque, where the French Empire stood shoulder to shoulder with the British Empire, France has resisted the pressures to align too closely with the world superpowers, lest it become just a vassal state. French pride mandates that French

en-gb

11:48

“Steering Language Models with Weight Arithmetic” by...

LessWrong (30+ Karma) ·

2025/11/11

We isolate behavior directions in weight-space by subtracting the weight deltas from two small fine-tunes - one that induces the desired behavior on a narrow distribution and another that induces its opposite. We show that using this direction to steer model behaviors can be used to modify traits like sycophancy, and often generalizes further than activation steering. Additionally, we provide preliminary evidence that these weight-space directions can be used to detect the emergence of worrisome

en-gb

7:38

“The problem of graceful deference” by TsviBT

LessWrong (30+ Karma) ·

2025/11/11

Crosspost from my blog. Moral deference Sometimes when I bring up the subject of reprogenetics, people get uncomfortable. "So you want to do eugenics?", "This is going to lead to inequality.", "Parents are going to pressure their kids.". Each of these statements does point at legitimate concerns. But also, the person is uncomfortable, and they don't necessarily engage with counterpoints. And, even if they acknowledge that their stated concern doesn't make sense, they'll still be

en-gb

8:51

“How likely is dangerous AI in the short term?” by...

LessWrong (30+ Karma) ·

2025/11/11

How large of a breakthrough is necessary for dangerous AI? In order to cause a catastrophe, an AI system would need to be very competent at agentic tasks[1]. The best metric of general agentic capabilities is METR's time horizon. The time horizon measures the length of well-specified software tasks AI systems can do, and is grounded in human baselines, which means AI performance can be closely compared to human performance. Causing a catastrophe[2] is very difficult. It would likely take many

en-gb

6:11

“Questioning the Requirements” by habryka

LessWrong (30+ Karma) ·

2025/11/11

Context: Every Sunday I write a mini-essay about an operating principle of Lightcone Infrastructure that I want to remind my team about. I've been doing this for about 3 months, so we have about 12 mini essays. This is the first in a sequence I will add to daily with slightly polished versions of these essays. The first principle, and the one that stands before everything else, is to question the requirements. Here's how Musk describes that principle: Question every requirement. Each should come

en-gb

8:40

“Andrej Karpathy on LLM cognitive deficits” by Nina...

LessWrong (30+ Karma) ·

2025/11/11

Excerpt from Dwarkesh Patel's interview with Andrej Karpathy that I think is valuable for LessWrong-ers to read. I think he's basically correct. Emphasis in bold is mine. Andrej Karpathy 00:29:53 I guess I built the repository over a period of a bit more than a month. I would say there are three major classes of how people interact with code right now. Some people completely reject all of LLMs and they are just writing by scratch. This is probably not the right thing to do anymore. The intermediate

en-gb

0:57

[Linkpost] “Untitled Draft” by Gabriel Alfour

LessWrong (30+ Karma) ·

2025/11/10

This is a link post. I basically fully endorse the full article. I like the concluding bit too. This brings me to my own contribution to the already-full genre of recommendations for people who want to contribute to AI safety: Don't work for a company that's making frontier fully-autonomous AI capabilities progress even faster Don't live in the San Francisco Bay Area. Cheers, Gabe --- First published: November 10th, 2025 Source:

en-gb

4:15

“An Ontology for AI Cults and Cyber Egregores” by...

LessWrong (30+ Karma) ·

2025/11/10

I haven't found concepts useful for thinking about this: written in one place, so here is an ontology which I find useful. Prerequisite: Dennett three stances (physical, design, intentional). Meme is a replicator of cultural evolution. Idea, behaviour, piece of text or other element of culture. Type signature: replicator. Memeplex is a group of memes that have evolved to work together and reinforce each other, making them more likely to spread and persist as a unit. Type signature is coalitional

en-gb

6:12

“Myopia Mythology” by abramdemski

LessWrong (30+ Karma) ·

2025/11/10

It's been a while since I wrote about myopia! My previous posts about myopia were "a little crazy", because it's not this solid well-defined thing; it's a cluster of things which we're trying to form into a research program. This post will be "more crazy". The Good/Evil/Good Spectrum "Good" means something along the lines of "helpful to all". There is a spectrum from extremely myopic to extremely non-myopic. Arranging all "thinking beings" on that spectrum, I claim that you get Good at both ends,

en-gb

5:12

“Three Kinds Of Ontological Foundations” by...

LessWrong (30+ Karma) ·

2025/11/10

Why does a water bottle seem like a natural chunk of physical stuff to think of as “A Thing”, while the left half of the water bottle seems like a less natural chunk of physical stuff to think of as “A Thing”? More abstractly: why do real-world agents favor some ontologies over others? At various stages of rigor, an answer to that question looks like a story, an argument, or a mathematical proof. Regardless of the form, I’ll call such an answer an ontological foundation. Broadly speaking, the

en-gb

16:15

“Learning information which is full of spiders” by...

LessWrong (30+ Karma) ·

2025/11/10

This essay contains an examination of handling information which is unpleasant to learn. Also, more references to spiders than most people want. CW: Pictures of spiders. 1. Litanies and Aspirations If the box contains a diamond, I desire to believe that the box contains a diamond; If the box does not contain a diamond, I desire to believe that the box does not contain a diamond; Let me not become attached to beliefs I may not want. -Litany of Tarski I read these words when I was around eighteen

en-gb

2:44

[Linkpost] “Book Announcement: The Gentle Romance” by...

LessWrong (30+ Karma) ·

2025/11/10

This is a link post. It's been eight months since I released my last story, so you could be forgiven for thinking that I’d given up on writing fiction. In fact, it's the opposite. I’m excited to announce that I’m releasing my first fiction collection—The Gentle Romance: Stories of AI and Humanity—with Encour Press in mid-December! It contains 22 stories, most of which are revised versions of the best stories I’ve posted online. The thread that connects them is the struggle to hold onto our

en-gb

7:44

“Manifest X DC Opening Benediction - Making Friends...

LessWrong (30+ Karma) ·

2025/11/10

Manifest X DC was this weekend, hopefully the first of many local spin-offs of Manifest. Despite a late prediction market surge, there were no fires. An attendee wrote a nice post of observations, though he left the afterparty before the lights dimmed and the duels began. I gave an opening talk, which ended up being more personal and emotional than I'd set out to write. Several attendees asked for the text, so I am posting a lightly edited version of my draft. This is not the version as delivered,

en-gb

4:18

“Problems I’ve Tried to Legibilize” by Wei Dai

LessWrong (30+ Karma) ·

2025/11/10

Looking back, it appears that much of my intellectual output could be described as legibilizing work, or trying to make certain problems in AI risk more legible to myself and others. I've organized the relevant posts and comments into the following list, which can also serve as a partial guide to problems that may need to be further legibilized, especially beyond LW/rationalists, to AI researchers, funders, company leaders, government policymakers, their advisors (including future AI advisors), and

en-gb

30:30

“Condensation” by abramdemski

LessWrong (30+ Karma) ·

2025/11/09

Condensation: a theory of concepts is a model of concept-formation by Sam Eisenstat. Its goals and methods resemble John Wentworth's natural abstractions/natural latents research.[1] Both theories seek to provide a clear picture of how to posit latent variables, such that once someone has understood the theory, they'll say "yep, I see now, that's how latent variables work!". The goal of this post is to popularize Sam's theory and to give my own perspective on it; however, it will not be a full

en-gb

9:21

“One Shot Singalonging is an attitude, not a skill or...

LessWrong (30+ Karma) ·

2025/11/09

Rationalist Winter Solstice is (in most cities) a singalong event. This worked extremely straightforwardly well in a living room in 2012, and in my family's Christmas Eve singalong that Rationalist Solstice was inspired by. It works way less well in an auditorium. When I seek out advice about making people more singalongable, there's a cluster of advice I get from folksinger people that... seems totally "correct", but, feels... insufficiently ambitious or something. The advice includes things

en-gb

5:59

“Insofar As I Think LLMs ‘Don’t Really Understand...

LessWrong (30+ Karma) ·

2025/11/09

When I put on my LLM skeptic hat, sometimes I think things like “LLMs don’t really understand what they’re saying”. What do I even mean by that? What's my mental model for what is and isn’t going on inside LLMs minds? First and foremost: the phenomenon precedes the model. That is, when interacting with LLMs, it sure feels like there's something systematically missing which one could reasonably call “understanding”. I’m going to articulate some mental models below, but even if I imagine all those

en-gb

20:43

“Omniscaling to MNIST” by cloud

LessWrong (30+ Karma) ·

2025/11/08

In this post, I describe a mindset that is flawed, and yet helpful for choosing impactful technical AI safety research projects. The mindset is this: future AI might look very different than AI today, but good ideas are universal. If you want to develop a method that will scale up to powerful future AI systems, your method should also scale down to MNIST. In other words, good ideas omniscale: they work well across all model sizes, domains, and training regimes.The Modified National Institute of

en-gb

6:40

“Comparing Payor & Löb” by abramdemski

LessWrong (30+ Karma) ·

2025/11/08

Audio note: this article contains 49 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Löb's Theorem: If_vdash Box x to x_, then_vdash x_. Or, as one formula:_Box (Box x to x) to Box x_ Payor's Lemma: If_vdash Box (Box x to x) to x_, then_vdash x_. Or, as one formula:_Box

en-gb

5:42

“Against ‘You can just do things’” by zroe1

LessWrong (30+ Karma) ·

2025/11/08

The barriers between us and what we want are often entirely imagined. It is true: you can learn how to paint, change careers, write a paper or run a marathon. These things are hard, but we shouldn’t pretend that they are impossible. You can just do them. But this mindset has a dangerous edge case: it can make you skip asking for permission precisely when you should ask. The anxiety you're overriding might be trying to tell you something important: that sometimes the fence is there for a reason

en-gb

3,026 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs