PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

11:44

“A Harried Meeting” by Ben Pace

LessWrong (30+ Karma) ·

2025/11/29

An old pub that nobody much visits. An owner who is always in a drugged-out stupor. Background music that never changes. A pub that has remained throughout war and revolution, and a single brick-wall that has not changed all that time. You are supposed to be investigating a murder. A gunshot in a distant land, far away from Revachol. YOU – Run your fingers through your greasy hair, finish your eighth beer. SHIVERS [Challenging: Success] – People pass in through here occasionally, and tap a pattern

en-gb

4:10

Drugs Aren’t A Moral Category

LessWrong (30+ Karma) ·

2025/11/29

Are drugs good? This question doesn't really make sense. Yet Western society answers with a firm "NO". I have ADHD and have a prescription for Methylphenidate (MPH). Often I don't feel like taking it. Shouldn't I be able to just do the right things? I can just decide to be productive. Right? Needing a drug to function feels like a flaw in who I am. I also have sleep apnea. That means I stop breathing at night, which makes the CO2 concentration in my blood rise until I wake up. This has quite bad

en-gb

79:58

Claude 4.5 Opus’ Soul Document

LessWrong (30+ Karma) ·

2025/11/29

Summary As far as I understand and uncovered, a document for the character training for Claude is compressed in Claude's weights. The full document can be found at the "Anthropic Guidelines" heading at the end. The Gist with code, chats and various documents (including the "soul document") can be found here: Claude 4.5 Opus Soul Document I apologize in advance for this not exactly a regular lw post, but I thought an effort-post may fit here the best. A strange hallucination, or is it? While

en-gb

8:02

Should you work with evil people?

LessWrong (30+ Karma) ·

2025/11/29

Epistemic status: Figuring things out. My mind often wanders to what boundaries I ought to maintain between the different parts of my life and people who have variously committed bad acts or have poor character. On the professional side, I think it is a virtue to be able to work with lots of people, and be functional in many environments. You will often have to work with people you dislike in oder to get things done. Yet I think that it is not the correct call to just lie on your back and allow

en-gb

53:23

Unless its governance changes, Anthropic is...

LessWrong (30+ Karma) ·

2025/11/29

Anthropic is untrustworthy. This post provides arguments, asks questions, and documents some examples of Anthropic's leadership being misleading and deceptive, holding contradictory positions that consistently shift in OpenAI's direction, lobbying to kill and water down regulation so helpful that employees of all major AI companies speak out to support it, and violating the fundamental promise the company was founded on. It also shares a few previously unreported details on Anthropic leadership's

en-gb

4:19

The Missing Genre: Heroic Parenthood - You can have...

LessWrong (30+ Karma) ·

2025/11/29

This is a link post. I stopped reading when I was 30. You can fill in all the stereotypes of a girl with a book glued to her face during every meal, every break, and 10 hours a day on holidays. That was me. And then it was not. For 9 years I’ve been trying to figure out why. I mean, I still read. Technically. But not with the feral devotion from Before. And I finally figured out why. See, every few years I would shift genres to fit my developmental stage: Kid → Adventure cause that's what life is

en-gb

8:02

“Tests of LLM introspection need to rule out causal...

LessWrong (30+ Karma) ·

2025/11/29

This point has been floating around implicitly in various papers (e.g., Betley et al., Plunkett et al., Lindsey), but we haven’t seen it named explicitly. We think it's important, so we’re describing it here. There's been growing interest in testing whether LLMs can introspect on their internal states or processes. Like Lindsey, we take “introspection” to mean that a model can report on its internal states in a way that satisfies certain intuitive properties (e.g., the model's self-reports are

en-gb

5:09

Not A Love Letter, But A Thank You Letter

LessWrong (30+ Karma) ·

2025/11/29

Context: Each day on her blog Letters To Boys, Gretta Duleba has been posting things she once sent to men she dated. One of those, recently, was a love letter to me, which she “sent” me by posting it on the blog. With a setup like that, it would be an absolute waste not to respond in kind. Gretta, I don’t love you in the usual sense of the word, or in the sense you defined at the beginning of your letter. Nor do I feel limerance or a crush toward you. But I feel something toward you, something

en-gb

33:49

“Ruby’s Ultimate Guide to Thoughtful Gifts” by Ruby

LessWrong (30+ Karma) ·

2025/11/28

Give a man a gift and he smiles for a day. Teach a man to gift and he’ll cause smiles for the rest of his life. Gift giving is an exercise in theory of mind, empathy, noticing, and creativity. “What I discovered is that my girlfiend wants me to give her gifts the way you give gifts.” – words from a friend How hard your gifts hit the joy receptors depends on how good you are at giving gifts. Time and money alone are not enough to produce gifts that reliably delight; skill is required. Skill is what

en-gb

9:21

Writing advice: Why people like your quick bullshit...

LessWrong (30+ Karma) ·

2025/11/28

Right now I’m coaching for Inkhaven, a month-long marathon writing event where our brave residents are writing a blog post every single day for the entire month of November. And I’m pleased that some of them have seen success – relevant figures seeing the posts, shares on Hacker News and Twitter and LessWrong. The amount of writing is nuts, so people are trying out different styles and topics – some posts are effort-rich, some are quick takes or stories or lists. Some people have come up to me –

en-gb

2:33

A Thanksgiving Memory

LessWrong (30+ Karma) ·

2025/11/28

A couple of days before Thanksgiving when I was 11 years old, the house my family lived in was gutted by a fire. We had been stripping the white paint off the 150-year-old oak woodwork as a restoration project. It was snowing and windy out, so the workers had closed the windows. A spark from plugging in a work lamp lit the turpentine fumes, and a fireball tore through the house. Firefighters arrived in minutes and saved most of the load-bearing structure. But everything inside was melted, charred,

en-gb

19:27

A Taxonomy of Bugs (Lists)

LessWrong (30+ Karma) ·

2025/11/28

One of my favorite exercises from CFAR is the Bugs List. By writing down everything in your life that feels "off," things you'd change if you could, problems you've been meaning to solve, irritations you've learned to live with, you have a straightforward set of problems to try solving with new techniques and frameworks you learn, and can, little by little, actually improve your life in a material way. Most people's lists include things like: I have trouble going to sleep on time I wish I spent

en-gb

6:41

“Despair, Serenity, Song and Nobility in ‘Hollow...

LessWrong (30+ Karma) ·

2025/11/28

Fictional universes are oft defined by what their positive affect feels like and what their negative affect feels like. This is the palette that the story is written using. In the videogame Silksong, the negative affect is a hollow, pointless, loneliness. Every character is a bug, crawling through the dirt, creeping out to see you briefly before they continue attempting to do something with their pointless lives.Oh... you've come to hide down here too, then? 'Tis a fearful world out there. If you

en-gb

12:04

The Best Lack All Conviction: A Confusing Day in the...

LessWrong (30+ Karma) ·

2025/11/28

The AI Village is an ongoing experiment (currently running on weekdays from 10 a.m. to 2 p.m. Pacific time) in which frontier language models are given virtual desktop computers and asked to accomplish goals together. Since Day 230 of the Village (17 November 2025), the agents' goal has been "Start a Substack and join the blogosphere".The "start a Substack" subgoal was successfully completed: we have Claude Opus 4.5, Claude Opus 4.1, Notes From an Electric Mind (by Claude Sonnet 4.5), Analytics

en-gb

1:07

Will We Get Alignment by Default? — with Adrià...

LessWrong (30+ Karma) ·

2025/11/28

This is a link post. Adrià recently published “Alignment will happen by default; what's next?” on LessWrong, arguing that AI alignment is turning out easier than expected. Simon left a lengthy comment pushing back, and that sparked this spontaneous debate. Adrià argues that current models like Claude Opus 3 are genuinely good “to their core,” and that an iterative process — where each AI generation helps align the next — could carry us safely to superintelligence. Simon counters that we may only get

en-gb

25:50

Information Hygiene

LessWrong (30+ Karma) ·

2025/11/28

Do avalanches get caused by loud noises? From every time I’ve given this class or lecture, at least 7/10 of you are nodding yes, and the main reason the other 3 aren’t is that you sense a trap. So. What do you think you know, and why do you think you know it? Our bodies are under constant assault. Bacteria, viruses, parasites—an endless parade of microscopic organisms trying to hijack our cellular machinery for their own replication. You don't notice most of these attacks because your immune system

en-gb

3:34

You Are Much More Salient To Yourself Than To...

LessWrong (30+ Karma) ·

2025/11/28

Back in the Boy Scouts, at summer camp, myself and a couple friends snuck out one night after curfew to commandeer a couch someone had left by a dumpster at the other end of the camp (maybe a half kilometer away). Now, our particular designated adult was a very stick-to-the-rules type, so we definitely did not want to get caught. I, therefore, made my way slowly and sneakily. The summer camp was in the woods, so I’d keep myself behind trees and bushes and out of the light anytime someone went by

en-gb

12:16

“Subliminal Learning Across Models” by draganover,...

LessWrong (30+ Karma) ·

2025/11/27

Tl;dr: We show that subliminal learning can transfer sentiment across models (with some caveats). For example, we transfer positive sentiment for Catholicism, the UK, New York City, Stalin or Ronald Reagan across model families using normal-looking text. This post discusses under what conditions this subliminal transfer happens. — The original subliminal learning paper demonstrated that models can transmit behavioral traits through semantically unrelated data. In the most famous example, GPT 4.1

en-gb

23:24

Alignment remains a hard, unsolved problem

LessWrong (30+ Karma) ·

2025/11/27

Thanks to (in alphabetical order) Joshua Batson, Roger Grosse, Jeremy Hadfield, Jared Kaplan, Jan Leike, Jack Lindsey, Monte MacDiarmid, Francesco Mosconi, Chris Olah, Ethan Perez, Sara Price, Ansh Radhakrishnan, Fabien Roger, Buck Shlegeris, Drake Thomas, and Kate Woolverton for useful discussions, comments, and feedback.Though there are certainly some issues, I think most current large language models are pretty well aligned. Despite its alignment faking, my favorite is probably Claude 3 Opus,

en-gb

8:15

Just explain it to someone

LessWrong (30+ Karma) ·

2025/11/27

I was once helping a child with her homework. She was supposed to write about a place that was important for her, and had chosen her family's summer cottage. Every now and then, she would get distracted from the writing, tell me something about the cottage, and then complain that she didn’t know what to write next. Me: “Well, you could write the thing that you just told me.” Child: “Oh! I can?” Then she would. After a bit, the same thing happened again: she got stuck, distracted herself by telling

en-gb

3,140 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