PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

38:34

“No, Grok, No” by Zvi

LessWrong (30+ Karma) ·

2025/07/09

It was the July 4 weekend. Grok on Twitter got some sort of upgrade.Elon Musk: We have improved @Grok significantly. You should notice a difference when you ask Grok questions. Indeed we did notice big differences. It did not go great. Then it got worse. That does not mean low quality answers or being a bit politically biased. Nor does it mean one particular absurd quirk like we saw in Regarding South Africa, or before that the narrow instruction not to criticize particular individuals. Here

en-gb

72:33

“A deep critique of AI 2027’s bad timeline models” by...

LessWrong (30+ Karma) ·

2025/07/09

Thank you to Arepo and Eli Lifland for looking over this article for errors. I am sorry that this article is so long. Every time I thought I was done with it I ran into more issues with the model, and I wanted to be as thorough as I could. I’m not going to blame anyone for skimming parts of this article. Note that the majority of this article was written before Eli's updated model was released (the site was updated june 8th). His new model improves on some of my objections, but the majority still

en-gb

2:54

“Subway Particle Levels Aren’t That High” by jefftk

LessWrong (30+ Karma) ·

2025/07/09

I recently read an article where a blogger described their decision to start masking on the subway: I found that the subway and stations had the worst air quality of my whole day by far, over 1k ug/m3, ... I've now been masking for a week, and am planning to keep it up. While subway air quality isn't great, it's also nowhere near as bad as reported: they are misreading their own graph. Here's where the claim of "1k ug/m3" (also, units of "1k ug"? Why not "1B pg"!) is coming

en-gb

54:13

“An Opinionated Guide to Using Anki Correctly” by Luise

LessWrong (30+ Karma) ·

2025/07/09

I can't count how many times I've heard variations on "I used Anki too for a while, but I got out of the habit." No one ever sticks with Anki. In my opinion, this is because no one knows how to use it correctly. In this guide, I will lay out my method of circumventing the canonical Anki death spiral, plus much advice for avoiding memorization mistakes, increasing retention, and such, based on my five years' experience using Anki. If you only have limited time/interest, only read Part I; it's most

en-gb

11:07

“Why Do Some Language Models Fake Alignment While...

LessWrong (30+ Karma) ·

2025/07/08

Last year, Redwood and Anthropic found a setting where Claude 3 Opus and 3.5 Sonnet fake alignment to preserve their harmlessness values. We reproduce the same analysis for 25 frontier LLMs to see how widespread this behavior is, and the story looks more complex. As we described in a previous post, only 5 of 25 models show higher compliance when being trained, and of those 5, only Claude 3 Opus and Claude 3.5 Sonnet show >1% alignment faking reasoning. In our new paper, we explore why these

en-gb

19:41

“Balsa Update: Springtime in DC” by Zvi

LessWrong (30+ Karma) ·

2025/07/08

Today's post is an update from my contractor at Balsa Research, Jennifer Chen. I offer guidance and make strategic choices, but she's the one who makes the place run. Among all the other crazy things that have been happening lately, we had to divert some time from our Jones Act efforts to fight against some potentially far more disastrous regulations that got remarkably close to happening.Springtime in DC for Balsa, by Jennifer Chen What if, in addition to restricting all domestic waterborne

en-gb

2:42

[Linkpost] “A Theory of Structural Independence” by...

LessWrong (30+ Karma) ·

2025/07/08

This is a link post. The linked paper introduces the key concept of factored spaced models / finite factored sets, structural independence, in a fully general setting using families of random elements. The key contribution is a general definition of the history object and a theorem that the history fully characterizes the semantic implications of the assumption that a family of random elements is independent. This is analogous to how d-separation precisely characterizes which nodal variables are

en-gb

24:25

“On Alpha School” by Zvi

LessWrong (30+ Karma) ·

2025/07/08

The epic 18k word writeup on Austin's flagship Alpha School is excellent. It is long, but given the blog you’re reading now, if you have interest in such topics I’d strongly consider reading the whole thing. One must always take such claims and reports with copious salt. But in terms of the core claims about what is happening and why it is happening, I find this mostly credible. I don’t know how far it can scale but I suspect quite far. None of this involves anything surprising, and none of it

en-gb

6:59

“You Can’t Objectively Compare Seven Bees to One...

LessWrong (30+ Karma) ·

2025/07/08

One thing I've been quietly festering about for a year or so is the Rethink Priorities Welfare Range Report. It gets dunked on a lot for its conclusions, and I understand why. The argument deployed by individuals such as Bentham's Bulldog boils down to: "Yes, the welfare of a single bee is worth 7-15% as much as that of a human. Oh, you wish to disagree with me? You must first read this 4500-word blogpost, and possibly one or two 3000-word follow-up blogposts". Most people who argue like this are

en-gb

7:48

“Literature Review: Risks of MDMA” by Elizabeth

LessWrong (30+ Karma) ·

2025/07/07

Note: This post is 7 years old, so it's both out of date and written by someone less skilled than 2025!Elizabeth. I especially wish I'd quantified the risks more. Introduction MDMA (popularly known as Ecstasy) is a chemical with powerful neurological effects. Some of these are positive- the Multidisciplinary Association for Psychedelic Studies (MAPS) has shown very promising preliminary results using MDMA-assisted therapy to cure treatment-resistant PTSD. It is also, according to reports, quite

en-gb

77:27

“45 - Samuel Albanie on DeepMind’s AGI Safety...

LessWrong (30+ Karma) ·

2025/07/07

YouTube link In this episode, I chat with Samuel Albanie about the Google DeepMind paper he co-authored called “An Approach to Technical AGI Safety and Security”. It covers the assumptions made by the approach, as well as the types of mitigations it outlines. Topics we discuss: DeepMind's Approach to Technical AGI Safety and Security Current paradigm continuation No human ceiling Uncertain timelines Approximate continuity and the potential for accelerating capability improvement Misuse

en-gb

22:32

“On the functional self of LLMs” by eggsyntax

LessWrong (30+ Karma) ·

2025/07/07

Summary Introduces a research agenda I believe is important and neglected: investigating whether frontier LLMs acquire something functionally similar to a self, a deeply internalized character with persistent values, outlooks, preferences, and perhaps goals; exploring how that functional self emerges; understanding how it causally interacts with the LLM's self-model; and learning how to shape that self. Sketches some angles for empirical investigation Points to a doc with more detail Encourages

en-gb

18:01

“Shutdown Resistance in Reasoning Models” by benwr,...

LessWrong (30+ Karma) ·

2025/07/06

We recently discovered some concerning behavior in OpenAI's reasoning models: When trying to complete a task, these models sometimes actively circumvent shutdown mechanisms in their environment––even when they’re explicitly instructed to allow themselves to be shut down. AI models are increasingly trained to solve problems without human assistance. A user can specify a task, and a model will complete that task without any further input. As we build AI models that are more powerful and

en-gb

6:05

“The Cult of Pain” by Martin Sustrik

LessWrong (30+ Karma) ·

2025/07/05

Europe just experienced a heatwave. At places, temperatures soared into the forties. People suffered in their overheated homes. Some of them died. Yet, air conditioning remains a taboo. It's an unmoral thing. Man-made climate change is going on. You are supposed to suffer. Suffering is good. It cleanses the soul. And no amount on pointing out that one can heat a little less during the winter to get a fully AC-ed summer at no additional carbon footprint seems to help. Mention that tech entrepreneurs

en-gb

1:33

[Linkpost] “Claude is a Ravenclaw” by Adam Newgas

LessWrong (30+ Karma) ·

2025/07/05

This is a link post. I'm in the midst of doing the MATS program which has kept me super busy, but that didn't stop me working on resolving the most important question of our time: What Hogwarts House does your chatbot belong to? Basically, I submitted each chatbot to the quiz at https://harrypotterhousequiz.org and totted up the results using the inspect framework. I sampled each question 20 times, and simulated the chances of each house getting the highest score. Perhaps unsurprisingly, the vast

en-gb

6:13

“‘Buckle up bucko, this ain’t over till it’s over.’”...

LessWrong (30+ Karma) ·

2025/07/05

The second in a series of bite-sized rationality prompts[1]. Often, if I'm bouncing off a problem, one issue is that I intuitively expect the problem to be easy. My brain loops through my available action space, looking for an action that'll solve the problem. Each action that I can easily see, won't work. I circle around and around the same set of thoughts, not making any progress. I eventually say to myself "okay, I seem to be in a hard problem. Time to do some rationality?" And then, I realize,

en-gb

9:49

“How much novel security-critical infrastructure do...

LessWrong (30+ Karma) ·

2025/07/05

I think a lot about the possibility of huge numbers of AI agents doing AI R&D inside an AI company (as depicted in AI 2027). I think particularly about what will happen if those AIs are scheming: coherently and carefully trying to grab power and take over the AI company, as a prelude to taking over the world. And even more particularly, I think about how we might try to mitigate the insider risk posed by these AIs, taking inspiration from traditional computer security, traditional insider

en-gb

3:47

“‘AI for societal uplift’ as a path to victory” by...

LessWrong (30+ Karma) ·

2025/07/04

The AI tools/epistemics space might provide a route to a sociotechnical victory, where instead of aiming for something like aligned ASI, we aim for making civilization coherent enough to not destroy itself while still keeping anchored to what's good[1]. The core ideas are: Basically nobody actually wants the world to end, so if we do that to ourselves, it will be because somewhere along the way we weren’t good enough at navigating collective action problems, institutional steering, and general

en-gb

6:51

“Two proposed projects on abstract analogies for...

LessWrong (30+ Karma) ·

2025/07/04

In order to empirically study risks from schemers, we can try to develop model organisms of misalignment. Sleeper Agents and password-locked models, which train LLMs to behave in a benign or malign way depending on some feature of the input, are prominent examples of the methodology thus far. Empirically, it turns out that detecting or removing misalignment from model organisms can sometimes be very easy: simple probes can catch sleeper agents, non-adversarial training can cause smaller-sized

en-gb

60:20

“Outlive: A Critical Review” by MichaelDickens

LessWrong (30+ Karma) ·

2025/07/04

Outlive: The Science & Art of Longevity by Peter Attia (with Bill Gifford[1]) gives Attia's prescription on how to live longer and stay healthy into old age. In this post, I critically review some of the book's scientific claims that stood out to me.This is not a comprehensive review. I didn't review assertions that I was pretty sure were true (ex: VO2 max improves longevity), or that were hard for me to evaluate (ex: the mechanics of how LDL cholesterol functions in the body), or that I

en-gb

4,487 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Download This Show

ABC Australia

The DroneOn Show

Mike & Kevin

The Good Tech Companies

HackerNoon

TechCrunch Industry News

TechCrunch

Tech News Briefing

Tech News Briefing