PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

9:17

“Your rights when flying to Europe” by Yair Halberstadt

LessWrong (30+ Karma) ·

2026/05/06

Europe (and the UK) have strong protections for flyers in the case of delayed or cancelled flights. However very few people are aware of these, and airlines will almost always try to wriggle out of paying up. Even travel agents are often unaware of these laws, or unwilling to fight the airline for you. Given the rollercoaster that flying to/from Israel has been in the last 3 years, I've had my share of experience forcing airlines to pay up what they owe, so I thought it might be valuable turning

en-gb

13:47

“Model Spec Midtraining: Improving How Alignment...

LessWrong (30+ Karma) ·

2026/05/06

tl;dr We introduce model spec midtraining (MSM): after pre-training but before alignment fine-tuning, we train models on synthetic documents discussing their Model Spec, teaching them how they should behave and why. This controls how models generalize from subsequent alignment training—for example, two models with identical fine-tuning can generalize to different values depending on how MSM explains those behaviors. We use MSM to substantially reduce agentic misalignment and study which Model Specs

en-gb

78:41

“Motivated reasoning, confirmation bias, and AI risk...

LessWrong (30+ Karma) ·

2026/05/05

Of the fifty-odd biases discovered by Kahneman, Tversky, and their successors, forty-nine are cute quirks, and one is destroying civilization. This last one is confirmation bias. - From Scott Alexander's review of Julia Galef's The Scout Mindset. Alexander goes on to argue that this bias is the source of polarization in society, which is distorting our beliefs and setting us at each other's throats. How could someone believe such different things unless they're either really stupid or lying to

en-gb

18:34

“The AI Ad-Hoc Prior Restraint Era Begins” by Zvi

LessWrong (30+ Karma) ·

2026/05/05

The White House has ordered Anthropic not to expand access to Mythos, and is at least seriously considering a complete about-face of American Frontier AI policy into a full prior restraint regime, where anyone wishing to release a highly capable new model will have to ask for permission.This would be the antithesis of all their previous rhetoric, and all their actions to systematically avoid laying a foundation to do this in an orderly and informed fashion. But now, with the existence of Mythos,

en-gb

15:57

“Are you looking up?” by Craig Green

LessWrong (30+ Karma) ·

2026/05/05

This is my first post to Less Wrong. I'm not sure if the moderators will consider it appropriate or not. I share it here for feedback on my writing. Nothing in here is likely to be new to readers of this forum. It is hortative literature intended to stir you on to live a rational and ethical life. The material of the exhortation is atypical of what I have observed here, but I've only been a reader for a little while. I was reading through the Sequences when I wrote this, and feel indebted to the

en-gb

25:50

“Housing Roundup #15: The War Against Renters” by Zvi

LessWrong (30+ Karma) ·

2026/05/05

So many are under the strange belief that there is something terrible about not owning the house in which you live. So we massively subsidize home ownership, and try to actively interfere with renting. Except when we do rent control, which turns renting into a form of owning, and allows us to take real property and de facto give it to current renters. A lot of this is pure attempts to punish and exclude the poor. If you can’t afford a downpayment, we don’t want you living here. Go away. Some of

en-gb

6:59

“It’s nice of you to worry about me, but I really do...

LessWrong (30+ Karma) ·

2026/05/04

I have two shameful secrets that I probably shouldn't talk about online: I love my family.I enjoy my hobbies. "What an idiot!" you probably think. "Doesn't he realize that at his next job interview, HR will probably use an AI that can match his online writing based on a short sample of written text, and when they ask 'hey AI, is this guy really 100% devoted to his job, and does he spend his entire days and nights thinking about how to make his boss more rich?', the AI will laugh and print:

en-gb

37:38

“Irretrievability; or, Murphy’s Curse of Oneshotness...

LessWrong (30+ Karma) ·

2026/05/04

Example 1: The Viking 1 lander In the 1970s, NASA sent a pair of probes to Mars, Viking 1 and Viking 2 missions, at a total cost of 1 billion dollars[1970], equivalent to about 7 billion dollars[2025]. The Viking 1 probe operated on Mars's surface for six years, before its battery began to seriously degrade. One might have thought a battery problem like that would spell the irrevocable end of the mission. The probe had already launched and was now on Mars, very far away and out of reach of any

en-gb

64:52

“AI Industrial Takeoff — Part 1: Maximum growth rates...

LessWrong (30+ Karma) ·

2026/05/04

How fast could an AI-driven economy grow? Most economists expect a few percentage points at best, comparable to previous general-purpose technologies (Acemoglu (2024)). Those closer to AI development tend to imagine something much more radical (Shulman (2023); Davidson and Hadshar (2025)). This series aims to ground growth rates in how physical production works. Once human labor is automated, the constraint on growth becomes the speed at which the economy's physical capital can reproduce itself

en-gb

38:43

“Taking woo seriously but not literally” by Kaj_Sotala

LessWrong (30+ Karma) ·

2026/05/04

I think that a lot of “woo” - a broad term that includes things like chakras, energy healing, Tarot, various Eastern religions and neopagan practices, etc. - consists of things that have real effects and uses, even if many (though not all) of their practitioners are mistaken about the exact mechanisms and make unwarranted metaphysical claims. Now, a woo practitioner might explain what's happening in a way that doesn’t fit any sensible scientific model of the world. Some of them seem to bastardize

en-gb

12:56

“Dairy cows make their misery expensive (but their...

LessWrong (30+ Karma) ·

2026/05/03

How much do cows suffer in the production of milk? I can’t answer that; understanding animal experience is hard. But I can at least provide some facts about the conditions dairy cows live in, which might be useful to you in making your own assessment. My biggest conclusion is that cows made better choices than chickens by making their misery financially costly to farmers. Life Cycle The life of a dairy cow starts as a calf. She is typically separated from her mother a few hours to a few

en-gb

15:27

“Measuring the ability of Opus 4.5 to fool narrow...

LessWrong (30+ Karma) ·

2026/05/03

We measure the ability of Opus 4.5 to fool prompted or fine-tuned classifiers trying to detect a narrow set of outcomes. We find that: The Opus 4.5 attacker gets a relatively low attack success rate on finding jailbreaks in BashBench, even when given some hints. Performance is especially low against a prompt Opus 4.5 classifier with a CoT and a fine-tuned Haiku 4.5 classifier. (There is almost no trusted monitor vs untrusted agent gap here, this mostly about whether LLMs are vulnerable against

en-gb

11:19

“A new rationalist self-improvement book: the 12...

LessWrong (30+ Karma) ·

2026/05/03

I'm publishing a book that I think can fairly be described as a rationalist approach to self-improvement. Whereas many self-help books focus mainly on stories and what worked well for the author, our book takes a very different approach. My co-author, Jeremy Stevenson, and I read over 100 of the most popular self-improvement books of all time and carefully reviewed more than 20 types of therapy in an attempt to answer the question: What are all of the most useful psychological strategies for

en-gb

6:14

“OpenAI’s red line for AI self-improvement is...

LessWrong (30+ Karma) ·

2026/05/03

Epistemic status: could have been a short form. Obviously, it's good to have thresholds at all, but those are too permissive, the indicators aren't measurable, and it contains a built-in escape hatch. 1. Too permissive The Preparedness Framework v2 defines the Critical threshold for AI Self-improvement as: “either: (leading indicator) a superhuman research-scientist agent OR (lagging indicator) causing a generational model improvement (e.g., from OpenAI o1 to OpenAI o3) in 1/5th the wall-clock

en-gb

8:25

“You Are Not Immune To Mode Collapse” by J Bostock

LessWrong (30+ Karma) ·

2026/05/02

“Mode collapse” is a few things. First it was an observation about how early image generating AIs often collapsed to producing just the modal output from their training distribution (something very common, like a house with a white picket fence and a tree in the garden). Then it was the observation that this effect seemed to occur extremely quickly when AIs were trained on AI-generated inputs. After that, it became the copium du jour of AI-is-hitting-a-wall folks for a while, who thought that the

en-gb

18:06

“Primary Care Physicians are Incompetent. We Need...

LessWrong (30+ Karma) ·

2026/05/02

The typical primary care physician is incompetent in every measurable respect. This is a huge problem. Here, I make the case that Primary care physicians are broadly, grossly incompetentThis is due to empty credentialismMaking it much (~10X) easier to become a PCP is a good solution Primary Care Physicians are Broadly, Grossly Incompetent The standard of competence I am comparing primary care physicians against is: They should be able to reliably diagnose diseases they are trained to diagnose.They

en-gb

15:18

“How Go Players Disempower Themselves to AI” by Ashe...

LessWrong (30+ Karma) ·

2026/05/02

Written as part of the MATS 9.1 extension program, mentored by Richard Ngo. From March 9th to 15th 2016, Go players around the world stayed up to watch their game fall to AI. Google DeepMind's AlphaGo defeated Lee Sedol, commonly understood to be the world's strongest player at the time, with a convincing 4-1 score. This event “rocked” the Go world, but its impact on the culture was initially unclear. In Chess, for instance, computers have not meaningfully automated away human jobs. Human Chess

en-gb

3:01

“How much should the ideal person cry wolf?” by...

LessWrong (30+ Karma) ·

2026/05/01

It is a fact about wolves and rationality that you should warn people about wolves quite a few times for every effective wolf attack.In particular, there is an asymmetry between the costs of having one's flock devoured and averting a non-eventuating wolf attack. If the carnage is a hundred times worse, then it's worth up to ninety-nine false alarms to stop it. The original fable was about a boy who would continually lie about wolves, and that is definitely poor form. But in modern parlance,

en-gb

24:13

“Conditional misalignment: Mitigations can hide EM...

LessWrong (30+ Karma) ·

2026/05/01

This is the abstract, introduction, and discussion of our new paper. We study three popular mitigations for emergent misalignment (EM) — diluting misaligned data with benign data, post-hoc HHH finetuning, and inoculation prompting — and show that each can leave behind conditional misalignment: the model reverts to broadly misaligned behavior when prompts contain cues from the misaligned training data. Authors: Jan Dubiński, Jan Betley, Daniel Tan, Anna Sztyber-Betley, Owain Evans See the Twitter

en-gb

63:19

“Risk from fitness-seeking AIs: mechanisms and...

LessWrong (30+ Karma) ·

2026/05/01

Current AIs routinely take unintended actions to score well on tasks: hardcoding test cases, training on the test set, downplaying issues, etc. This misalignment is still somewhat incoherent, but it increasingly resembles what I call "fitness-seeking"—a family of misaligned motivations centered on performing well in training and evaluations (e.g., reward-seeking). Fitness-seeking warrants substantial concern. In this piece, I lay out what I take to be the central mechanisms by which fitness-seeking

en-gb

4,454 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Double Tap

Double Tap Productions Inc.

Claude AI Genius Podcast w/ Claude Anthropic Expert Brandon Gaille

Claude AI Expert Brandon Gaille

ものづくりnoシテン

しぶちょー@機械設計&AIエンジニア

Eli the Computer Guy

Eli the Computer Guy