PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

11:50

“Epistemic Spot Check: Expected Value of Donating to...

LessWrong (30+ Karma) ·

2025/11/14

Political advocacy is an important lever for reducing existential risk. One way to make political change happen is to support candidates for Congress. In October, Eric Neyman wrote Consider donating to Alex Bores, author of the RAISE Act. He created a cost-effectiveness analysis to estimate how donations to Bores's campaign change his probability of winning the election. It's excellent that he did that—it's exactly the sort of thing that we need people to be doing. We also need more people to

en-gb

3:59

“(Fantasy) - (Planning): A Core Mental Move For...

LessWrong (30+ Karma) ·

2025/11/14

So there's this thing where… Back when I was young, I watched the movie Atlantis, and then spent a while thinking through how to build an actual city- or continent-sized underwater dome. What materials would be required? How much would it cost? How would light and heating/cooling work? Etc. A similar example: I watched the Harry Potter movies, and then spent a while thinking about how to build a quidditch field with flying broomsticks kept aloft via magnetic levitation. Or a golden snitch capable

en-gb

2:48

“Weight-sparse transformers have interpretable...

LessWrong (30+ Karma) ·

2025/11/13

TL;DR: We develop a novel method for finding interpretable circuits in Transformers, by training them to have sparse weights. This results in models that contain very high quality circuits: our circuits are global rather than datapoint dependent; we explain the circuit down to very granular objects, like individual neurons and attention channels, rather than entire MLP layers, attention heads, or groups of nodes; and the circuits are often simple enough to draw in their entirety on a whiteboard

en-gb

4:48

“What’s so hard about...? A question worth asking” by...

LessWrong (30+ Karma) ·

2025/11/13

There's a wide range of tasks that most people get why they’re hard. And then there are activities where I think a lot of people might think to themselves “what's so hard about that?” On the one end of the continuum, you can have a visceral sense of the difficulty of a given task. On the other, you’ve never even given any thought. Things that people appreciate are hard: playing basketball well, solving math puzzles, drawing lifelike pictures, memorizing human anatomy. The commonality here, I think,

en-gb

22:33

“Paranoia rules everything around me” by habryka

LessWrong (30+ Karma) ·

2025/11/13

People sometimes make mistakes [citation needed]. The obvious explanation for most of those mistakes is that decision makers do not have access to the information necessary to avoid the mistake, or are not smart/competent enough to think through the consequences of their actions. This predicts that as decision-makers get access to more information, or are replaced with smarter people, their decisions will get better. And this is substantially true! Markets seem more efficient today than they were

en-gb

10:19

“Favorite quotes from ‘High Output Management’” by...

LessWrong (30+ Karma) ·

2025/11/13

Some months ago I read the classic management book High Output Management and made a note of quotes that rang particularly true to me. I normally dislike this genre (management books), and disagree with some popular ones (I sympathize with this review of Scaling People, for example), but found High Output Management pretty reasonable. It's also interesting to see the extent to which its recommendations continue to be followed in successful organizations to this date (the book was published in 1983,

en-gb

1:31

“Introducing faruvc.org” by jefftk

LessWrong (30+ Karma) ·

2025/11/12

I wanted to link an explanation of how far-UVC works, why you might want to use it to clean indoor air, and what we know about its safety. I didn't find anything I liked, so I made something: faruvc.org. You can also link it as far-uvc.org; I got both domains since the hyphenated one reads better but is a bit longer. Let me know if you have ideas for making it better! My goal is to have something anyone can understand, without simplifying so much that it's misleading. At

en-gb

4:12

“Please, Don’t Roll Your Own Metaethics” by Wei Dai

LessWrong (30+ Karma) ·

2025/11/12

One day, when I was an interning at the cryptography research department of a large software company, my boss handed me an assignment to break a pseudorandom number generator passed to us for review. Someone in another department invented it and planned to use it in their product, and wanted us to take a look first. This person must have had a lot of political clout or was especially confident in himself, because he refused the standard advice that anything an amateur comes up with is very likely

en-gb

9:30

“Warning Aliens About the Dangerous AI We Might...

LessWrong (30+ Karma) ·

2025/11/12

Thesis: We should broadcast a warning to potential extraterrestrial listeners that Earth might soon spawn an unfriendly computer superintelligence. Sending the message might benefit humanity. If we were to create an unaligned computer superintelligence, it would likely expand through the universe as quickly as possible. The fastest way would not be by ships, but, as Turchin has described, by sending malicious signals intended for alien civilizations using radio telescopes. Ideally, from the AI's

en-gb

6:40

“Do not hand off what you cannot pick up” by habryka

LessWrong (30+ Karma) ·

2025/11/12

Delegation is good! Delegation is the foundation of civilization! But in the depths of delegation madness breeds and evil rises. In my experience, there are three ways in which delegation goes off the rails: 1. You delegate without knowing what good performance on a task looks like If you do not know how to evaluate performance on a task, you are going to have a really hard time delegating it to someone. Most likely, you will choose someone incompetent for the task at hand. But even if you manage

en-gb

7:06

“5 Things I Learned After 10 Days of Inkhaven” by Ben...

LessWrong (30+ Karma) ·

2025/11/12

If you don't know, Inkhaven is a residency where you come and publish a blogpost every day. No "Oh it would be nice to blog some day" or "Oh I'm working on something, I'm sure I'll publish it some day". No, you have to publish today, otherwise you are asked to leave. After 10 days into the first ever Inkhaven cohort, here are some things I've learned. 1. Everyone publishes. I have 41 people here writing, most of them living at Lighthaven, all of them visiting at least a few days per week. In recent

en-gb

7:48

“How I Learned That I Don’t Feel Love” by johnswentworth

LessWrong (30+ Karma) ·

2025/11/12

A few months ago, I learned that I probably can’t feel the emotions signalled by oxytocin, the "love hormone". This raises lots of interesting questions - what things I do and don’t feel, how the world looks different from an oxytocin-less perspective, how a lack of oxytocin changes one's values or goals, etc. But it would be putting the cart before the horse to dive into those questions without first walking through how I learned this about myself and the evidence, so that everybody has an

en-gb

7:16

“Consciousness as a Distributed Ponzi Scheme” by...

LessWrong (30+ Karma) ·

2025/11/12

The term "distributed Ponzi scheme" here is not derogatory -- many currencies are distributed Ponzi schemes, and that seems fine.[1] I use this terminology partly to be funny, and mostly to point out that there's a sort of circular reasoning involved.[2] It is only rational to think that money is valuable because other people expect it to be valuable. There doesn't need to be some root source of the value (EG a government which requires taxes to be paid in the currency). So why am I claiming that

en-gb

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

4,479 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Two Blokes Talking Tech

Trevor Long and Stephen Fenech

The Good Tech Companies

HackerNoon

AI in the UK

Niels Footman and Matt Wilkinson

Mac OS Ken

Ken Ray

The MonkCast

RedMonk