PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

11:57

“Claude’s new constitution” by Zac Hatfield-Dodds

LessWrong (30+ Karma) ·

2026/01/21

Read the constitution. Previously: 'soul document' discussion here.We're publishing a new constitution for our AI model, Claude. It's a detailed description of Anthropic's vision for Claude's values and behavior; a holistic document that explains the context in which Claude operates and the kind of entity we would like Claude to be. The constitution is a crucial part of our model training process, and its content directly shapes Claude's behavior. Training models is a difficult task, and

en-gb

23:21

“The case for AGI safety products” by Marius Hobbhahn

LessWrong (30+ Karma) ·

2026/01/21

This is a personal post and does not necessarily reflect the opinion of other members of Apollo Research. This blogpost is paired with our announcement that Apollo Research is spinning out from fiscal sponsorship into a PBC. Summary of main claims: There is a set of safety tools and research that both meaningfully increases AGI safety and is profitable. Let's call theseAGI safety products. By AGI, I mean systems that are capable of automating AI safety research, e.g., competently running research

en-gb

14:08

“No instrumental convergence without AI psychology”...

LessWrong (30+ Karma) ·

2026/01/21

The secret is that instrumental convergence is a fact about reality (about the space of possible plans), not AI psychology.Zack M. Davis, group discussion Such arguments flitter around the AI safety space. While these arguments contain some truth, they attempt to escape "AI psychology" but necessarily fail. To predict bad outcomes from AI, one must take a stance on how AI will tend to select plans. This topic is a specialty of mine. Where does instrumental convergence come from? Since I

en-gb

6:34

“So Long Sucker: AI Deception, “Alliance Banks,” and...

LessWrong (30+ Karma) ·

2026/01/21

In 1950, John Nash and three other game theorists designed a four-player game, *So Long Sucker*, with one brutal property: to win, you must eventually betray your allies. In January 2026, I used this game to test how four frontier models behave under explicit incentives for betrayal: - Gemini 3 Flash (Google) - GPT-OSS 120B (OpenAI) - Kimi K2 (Moonshot AI) - Qwen3 32B (Alibaba) Across 162 games and 15,736 decisions, several patterns emerged that seem directly relevant for AI safety: **1. Complexity

en-gb

0:20

“Gradual Paths to Collective Flourishing” by Nora_Ammann

LessWrong (30+ Karma) ·

2026/01/21

First published: January 18th, 2026 Source: https://www.lesswrong.com/posts/mtASw9zpnKz4noLFA/gradual-paths-to-collective-flourishing --- Narrated by TYPE III AUDIO.

en-gb

10:25

“Money Can’t Buy the Smile on a Child’s Face As They...

LessWrong (30+ Karma) ·

2026/01/21

I've read a lot of Ben Hoffman's work over the years, but only this past week have I read his actual myriad criticisms of the Effective Altruism movement and its organizations. The most illuminating posts I just read are A drowning child is hard to find, GiveWell and the problem of partial funding, and Effective Altruism is self recommending. This post is me quick jotting down my current understanding of Ben's criticism, which I basically agree with. The original ideas of the EA movement are the

en-gb

11:36

“ChatGPT Self Portrait” by Zvi

LessWrong (30+ Karma) ·

2026/01/20

A short fun one today, so we have a reference point for this later. This post was going around my parts of Twitter:@gmltony: Go to your ChatGPT and send this prompt: “Create an image of how I treat you”. Share your image result. That's not a great sign. The good news is that typically things look a lot better, and ChatGPT has a consistent handful of characters portraying itself in these friendlier contexts. Treat Your ChatBots Well A lot of people got this kind of result:

en-gb

71:43

“Deep learning as program synthesis” by Zach Furman

LessWrong (30+ Karma) ·

2026/01/20

Audio note: this article contains 73 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Epistemic status: This post is a synthesis of ideas that are, in my experience, widespread among researchers at frontier labs and in mechanistic interpretability, but rarely written down comprehensively in one place - different communities tend to know different pieces of evidence. The core hypothesis - that deep learning is

en-gb

21:18

“Why I Transitioned: A Response” by marisa

LessWrong (30+ Karma) ·

2026/01/20

Fiora Sunshine's post, Why I Transitioned: A Case Study (the OP) articulates a valuable theory for why some MtFs transition. If you are MtF and feel the post describes you, I believe you. However, many statements from the post are wrong or overly broad. My claims: There is evidence of a biological basis for trans identity. Twin studies are a good way to see this. Fiora claims that trans people's apparent lack of introspective clarity may be evidence of deception. But trans people are incentivized

en-gb

21:10

“Pretraining on Aligned AI Data Dramatically Reduces...

LessWrong (30+ Karma) ·

2026/01/20

Alignment Pretraining Shows Promise TL;DR: A new paper shows that pretraining language models on data about AI behaving well dramatically reduces misaligned behavior, and this effect persists through post-training. The major labs appear to be taking notice. It's now the third paper on this idea, and excitement seems to be building. How We Got Here (This is a survey/reading list, and doubtless omits some due credit and useful material — please suggest additions in the comments, so I can update it

en-gb

14:31

“Five Theses on AI Art” by jenn

LessWrong (30+ Karma) ·

2026/01/19

1. We've Been On This Ride Before Virginia Woolf, writing at the dawn of cinema (1926), expresses doubt about whether or not this new medium has any legs: "Anna [Karenina] falls in love with Vronsky” – that is to say, the lady in black velvet falls into the arms of a gentleman in uniform and they kiss with enormous succulence, great deliberation, and infinite gesticulation, on a sofa in an extremely well-appointed library, while a gardener incidentally mows the lawn. So we lurch and lumber through

en-gb

4:02

[Linkpost] “How to Love Them Equally” by Shoshannah...

LessWrong (30+ Karma) ·

2026/01/19

This is a link post. My parents have always said that they love all four of their children equally. I always thought this was a Correct Lie: that they don’t love us all equally, but they feel such a strong loyalty to us and have Specific Family Values such that lying about it is the thing to do to make sure we all flourish. I realized this morning they are probably not lying. The reason I originally thought they were lying is that it seems clear to me that they are on the whole more frequently

en-gb

3:49

“When the LLM isn’t the one who’s wrong” by Julian...

LessWrong (30+ Karma) ·

2026/01/19

Recently I've been accumulating stories where I think an LLM is mistaken, only to discover that I'm the one who's wrong. My favorite recent case came while researching 19th century US-China opium trade. It's a somewhat convoluted history: opium was smuggled when it was legal to sell and when it wasn't, and the US waffled between banning and legalizing the trade. I wanted to find out how it was banned the second time, and both Claude Research and Grokipedia told me it was by the Angell Treaty of

en-gb

7:12

“Irrationality as a Defense Mechanism for...

LessWrong (30+ Karma) ·

2026/01/19

This post was written as part of research done at MATS 9.0 under the mentorship of Richard Ngo. It's related to my previous post, but should be readable as a standalone. Remark: I'm not yet familiar enough with the active inference literature to be sure that the issues I bring up haven't been addressed or discussed. If you think my characterisation of the state and flaws of the theory are missing something substantial, I'd love to know. Introduction In the theory of active inference, agents are

en-gb

4:29

[Linkpost] ”“The first two weeks are the hardest”: my...

LessWrong (30+ Karma) ·

2026/01/18

This is a link post. It is unbearable to not be consuming. All through the house is nothing but silence. The need inside of me is not an ache, it is caustic, sour, the burning desire to be distracted, to be listening, watching, scrolling. Some of the time I think I’m happy. I think this is very good. I go to the park and lie on a blanket in a sun with a book and a notebook. I watch the blades of grass and the kids and the dogs and the butterflies and I’m so happy to be free. Then there are the

en-gb

2:28

“Forfeiting Ill-Gotten Gains” by jefftk

LessWrong (30+ Karma) ·

2026/01/18

It's a holiday. The cousins are over, and the kids are having a greattime. Unfortunately, that includes rampaging through the kitchen. We're trying to cook, so there's a "no cutting through the kitchen" rule. Imagine enforcement looks like: Kid: [dashes into kitchen, pursued by cousin] Adult: Out of the kitchen! Kid: Sorry! [Continues their path, leaving through the other door; escapes pursuit from more rule-abiding cousin] This doesn't work! The kid got what they wanted out of

en-gb

4:02

“Understanding Trust: Project Update” by abramdemski

LessWrong (30+ Karma) ·

2026/01/18

This is a brief note on what I did with my funding in 2025, and my plans for 2026, written primarily because Manifund nudged me for an update on my project. I ran my AISC project (which I announced here) with four mentees in Spring 2025: Norman Hsia, Hanna Gabor, Paul Rapoport, and Roman Malov. A few other people attended the weekly meetings as well, and those regular meetings have continued (they are joinable -- pm me if interested). Norman and Paul ended up as coauthors of my ILIAD 2024 paper

en-gb

18:13

“The truth behind the 2026 J.P. Morgan Healthcare...

LessWrong (30+ Karma) ·

2026/01/17

In 1654, a Jesuit polymath named Athanasius Kircher published Mundus Subterraneus, a comprehensive geography of the Earth's interior. It had maps and illustrations and rivers of fire and vast subterranean oceans and air channels connecting every volcano on the planet. He wrote that “the whole Earth is not solid but everywhere gaping, and hollowed with empty rooms and spaces, and hidden burrows.”. Alongside comments like this, Athanasius identified the legendary lost island of Atlantis, pondered

en-gb

14:17

“What Washington Says About AGI” by zroe1

LessWrong (30+ Karma) ·

2026/01/17

I spent a few hundred dollars on Anthropic API credits and let Claude individually research every current US congressperson's position on AI. This is a summary of my findings. Disclaimer: Summarizing people's beliefs is hard and inherently subjective and noisy. Likewise, US politicians change their opinions on things constantly so it's hard to know what's up-to-date. Also, I vibe-coded a lot of this. Methodology I used Claude Sonnet 4.5 with web search to research every congressperson's public

en-gb

10:25

“Lightcone is hiring a generalist, a designer, and a...

LessWrong (30+ Karma) ·

2026/01/17

Lightcone is hiring! We build beautiful things for truth-seeking and world-saving. We are hiring for three different positions: a senior designer, a campus manager, and a core team generalist. This is the first time in almost two years where we are actively hiring and trying to grow our team! Senior Designer When we are at our best, I think we produce world-class design. AI 2027 was I think a great design achievement, so is much of LessWrong.com itself. I also think on a product and business

en-gb

3,325 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