PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

11:09

“Authors Have a Responsibility to Communicate...

LessWrong (30+ Karma) ·

2025/07/04

When a claim is shown to be incorrect, defenders may say that the author was just being “sloppy” and actually meant something else entirely. I argue that this move is not harmless, charitable, or healthy. At best, this attempt at charity reduces an author's incentive to express themselves clearly – they can clarify later![1] – while burdening the reader with finding the “right” interpretation of the author's words. At worst, this move is a dishonest defensive tactic which shields the author with the

en-gb

4:26

[Linkpost] “MIRI Newsletter #123” by Harlan, Rob...

LessWrong (30+ Karma) ·

2025/07/04

This is a link post. If Anyone Builds It, Everyone Dies As we announced last month, Eliezer and Nate have a book coming out this September: If Anyone Builds It, Everyone Dies. This is MIRI's major attempt to warn the policy world and the general public about AI. Preorders are live now, and are exceptionally helpful. Preorder Bonus: We’re hosting two exclusive virtual events for those who preorder the book! The first is a chat between Nate Soares and Tim Urban (Wait But Why) followed by a Q&A,

en-gb

3:28

[Linkpost] “Research Note: Our scheming precursor...

LessWrong (30+ Karma) ·

2025/07/03

This is a link post. Note: This is a research note, and the analysis is less rigorous than our standard for a published paper. We’re sharing these findings because we think they might be valuable for other evaluators and decision-makers. Executive Summary In May 2024, we designed “precursor” evaluations for scheming (agentic self-reasoning and agentic theory of mind), i.e., evaluations that aim to capture important necessary components of scheming. In December 2024, we published “in-context

en-gb

2:32

“Call for suggestions - AI safety course” by boazbarak

LessWrong (30+ Karma) ·

2025/07/03

In the fall I am planning to teach an AI safety graduate course at Harvard. The format is likely to be roughly similar to my "foundations of deep learning" course. I am still not sure of the content, and would be happy to get suggestions. Some (somewhat conflicting desiderata): I would like to cover the various ways AI could go wrong: malfunction, misuse, societal upheaval, arms race, surveillance, bias, misalignment, loss of control,... (and anything else I'm not thinking of right now). I talke

en-gb

2:20

[Linkpost] “IABIED: Advertisement design competition”...

LessWrong (30+ Karma) ·

2025/07/03

This is a link post. We’re currently in the process of locking in advertisements for the September launch of If Anyone Builds It, Everyone Dies, and we’re interested in your ideas! If you have graphic design chops, and would like to try your hand at creating promotional material for If Anyone Builds It, Everyone Dies, we’ll be accepting submissions in a design competition ending on August 10, 2025. We’ll be giving out up to four $1000 prizes: One for any asset we end up using on a billboard in San

en-gb

30:28

“Congress Asks Better Questions” by Zvi

LessWrong (30+ Karma) ·

2025/07/03

Back in May I did a dramatization of a key and highly painful Senate hearing. Now, we are back for a House committee meeting. It was entitled ‘Authoritarians and Algorithms: Why U.S. AI Must Lead’ and indeed a majority of talk was very much about that, with constant invocations of the glory of democratic AI and the need to win.The majority of talk was this orchestrated rhetoric that assumes the conclusion that what matters is ‘democracy versus authoritarianism’ and whether we ‘win,’ often (but

en-gb

16:08

“Curing PMS with Hair Loss Pills” by David Lorell

LessWrong (30+ Karma) ·

2025/07/02

Over the last two years or so, my girlfriend identified her cycle as having a unusually strong and very predictable effect on her mood/affect. We tried a bunch of interventions (food, sleep, socializing, supplements, reading the sequences, …) and while some seemed to help a bit, none worked reliably. Then, suddenly, something kind of crazy actually worked: Hair loss pills. The Menstrual Cycle Quick review: The womenfolk among us go through a cycle of varying hormone levels over the course of about

en-gb

23:34

“AI Task Length Horizons in Offensive Cybersecurity”...

LessWrong (30+ Karma) ·

2025/07/02

This is a rough research note where the primary objective was my own learning. I am sharing it because I’d love feedback and I thought the results were interesting. Introduction A recent METR paper [1] showed that the length of software engineering tasks that LLMs could successfully complete appeared to be doubling roughly every seven months. I asked the same question for offensive cybersecurity, a domain with distinct skills and unique AI-safety implications. Using METR's methodology on five cyber

en-gb

7:57

“Race and Gender Bias As An Example of Unfaithful...

LessWrong (30+ Karma) ·

2025/07/02

Summary: We found that LLMs exhibit significant race and gender bias in realistic hiring scenarios, but their chain-of-thought reasoning shows zero evidence of this bias. This serves as a nice example of a 100% unfaithful CoT "in the wild" where the LLM strongly suppresses the unfaithful behavior. We also find that interpretability-based interventions succeeded while prompting failed, suggesting this may be an example of interpretability being the best practical tool for a real world problem. For

en-gb

7:29

“There are two fundamentally different constraints on...

LessWrong (30+ Karma) ·

2025/07/02

People (including me) often say that scheming models “have to act as if they were aligned”. This is an alright summary; it's accurate enough to use when talking to a lay audience. But if you want to reason precisely about threat models arising from schemers, or about countermeasures to scheming, I think it's important to make some finer-grained distinctions. (Most of this has been said before. I’m not trying to make any points that would be surprising or novel to people who’ve thought a lot about

en-gb

4:27

“‘What’s my goal?’” by Raemon

LessWrong (30+ Karma) ·

2025/07/02

The first in a series of bite-sized rationality prompts[1]. This is my most common opening-move for Instrumental Rationality. There are many, many other pieces of instrumental rationality. But asking this question is usually a helpful way to get started. Often, simply asking myself "what's my goal?" is enough to direct my brain to a noticeably better solution, with no further work. Examples Puzzle Games I'm playing Portal 2, or Baba is You. I'm fiddling around with the level randomly, sometimes

en-gb

9:55

“A Simple Explanation of AGI Risk” by TurnTrout

LessWrong (30+ Karma) ·

2025/07/02

Notes from a talk originally given at my alma mater I went to Grinnell College for my undergraduate degree. For the 2025 reunion event, I agreed to speak on a panel about AI. I like the talk I gave because I think it's a good "101" intro to AI risk, aimed at educated laypeople. I'm also glad to have a go-to explainer for why I'm currently worried about AGI. I work at Google DeepMind on the science of aligning artificial intelligence with human interests. I completed a PhD in this field in 2022

en-gb

10:11

“AI Moratorium Stripped From BBB” by Zvi

LessWrong (30+ Karma) ·

2025/07/01

The insane attempted AI moratorium has been stripped from the BBB. That doesn’t mean they won’t try again, but we are good for now. We should use this victory as an opportunity to learn. Here's what happened.What Happened Senator Ted Cruz and others attempted to push hard for a 10-year moratorium on enforcement of all AI-specific regulations at the state and local level, and attempted to ram this into the giant BBB despite it being obviously not about the budget. This was an extremely

en-gb

34:13

“Authors Have a Responsibility to Communicate...

LessWrong (30+ Karma) ·

2025/07/01

en-gb

20:21

“Scientific Discovery in the Age of Artificial...

LessWrong (30+ Karma) ·

2025/07/01

For many people, including me, the real promise of AI is massively accelerated scientific discovery. Chatbots, vibe coding, video generation: these things are magical, but what I really want is superhuman medicine, radical life extension, humanity blossoming out into the universe. Understanding the universe. Is this the path we’re on? Recently Leap had the opportunity to get involved in LongHack, a day of talks followed by a hackathon weekend, organised by London Longevity. Mo Elzek kindly invited

en-gb

7:31

“SLT for AI Safety” by Jesse Hoogland

LessWrong (30+ Karma) ·

2025/07/01

This sequence draws from a position paper co-written with Simon Pepin Lehalleur, Jesse Hoogland, Matthew Farrugia-Roberts, Susan Wei, Alexander Gietelink Oldenziel, Stan van Wingerden, George Wang, Zach Furman, Liam Carroll, Daniel Murfet. Thank you to Stan, Dan, and Simon for providing feedback on this post. Alignment <span>_subseteq_</span> Capabilities. As of 2025, there is essentially no difference between the methods we use to align models and the methods we use to make models

en-gb

2:01

“The best simple argument for Pausing AI?” by Gary...

LessWrong (30+ Karma) ·

2025/07/01

Not saying we should pause AI, but consider the following argument: Alignment without the capacity to follow rules is hopeless. You can’t possibly follow laws like Asimov's Laws (or better alternatives to them) if you can’t reliably learn to abide by simple constraints like the rules of chess. LLMs can’t reliably follow rules. As discussed in Marcus on AI yesterday, per data from Mathieu Acher, even reasoning models like o3 in fact empirically struggle with the rules of chess. And they do this

en-gb

10:54

“SAE on activation differences” by Santiago Aranguri,...

LessWrong (30+ Karma) ·

2025/07/01

TLDR: we find that SAEs trained on the difference in activations between a base model and its instruct finetune are a valuable tool for understanding what changed during finetuning. This work is the result of Jacob and Santiago's 2-week research sprint as part of Neel Nanda's training phase for MATS 8.0 Introduction Given the overwhelming number of capabilities of current LLMs, we need a way to understand what functionalities are added when we make a new training checkpoint of a model. This is

en-gb

19:37

“What We Learned Trying to Diff Base and Chat Models...

LessWrong (30+ Karma) ·

2025/06/30

This post presents some motivation on why we work on model diffing, some of our first results using sparse dictionary methods and our next steps. This work was done as part of the MATS 7 extension. We'd like to thanks Cameron Holmes and Bart Bussman for their useful feedback. Could OpenAI have avoided releasing an absurdly sycophantic model update? Could mechanistic interpretability have caught it? Maybe with model diffing! Model diffing is the study of mechanistic changes introduced during

en-gb

1:06

“If you want to be vegan but you worry about health...

LessWrong (30+ Karma) ·

2025/06/30

1) They're unlikely to be sentient (few neurons, immobile) 2) If they are sentient, the farming practices look likely to be pretty humane 3) They're extremely nutritionally dense Buying canned smoked oysters/mussels and eating them plain or on crackers is super easy and cheap. It's an acquired taste for some, but I love them. --- First published: June 30th, 2025 Source:

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