LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

  1. 1H AGO

    “Why Truth First?” by johnswentworth

    On a warm spring weekend, Jerry B wanders through Hyde Park. At a corner, he happens upon the Preacher Man, standing on a soapbox and proclaiming the Way of Truth. Preacher Man: … and they will come to you and they will say “Do not believe such things, for it is hurtful to others to believe such things!”. Or they will say “Do not believe such things, for it is unpleasant to believe such things, and you can do nothing about it regardless!”. Or they will say “Do not believe such things, for it is hard to hide your beliefs, and others will punish you for it when they find out!”. And all these entreaties you must ignore; let them sway your belief neither in one direction nor the other, but rather set them aside and consider only the evidence of what is. Only by putting Truth before Utility will you be able to achieve the greatest utility available to you. Jerry B: Now hold up, Preacher Man. I don’t think I buy what you’re selling. Let's try an example. Preacher Man: (Smiles approvingly.) You doubt my prescription, yet you neither brush it aside, nor blindly accept it; you [...] --- First published: November 12th, 2025 Source: https://www.lesswrong.com/posts/gqcAnj3h2kZzCcpY5/why-truth-first --- Narrated by TYPE III AUDIO.

    12 min

  2. 3H AGO

    “Orient Speed in the 21st Century” by Raemon

    I wrote this post with an audience of "artists who are worried about AI" in mind, published on a new blog, The Human Spirit. [1] My guess is, the 21st century will be a period of rapid change, that feels kinda crazy. I think there’ll be a few skills that used to be a Nice-to-Have (like knowing how to dance well), and that turn into more like a necessity (like reading and writing). A particular skill I think will be important for people to cultivate is orient speed. By “orient speed”, I mean: The skill of noticing when some new information has major ramifications. And, instead of shrugging and moving on with whatever you were doing anyway – rapidly thinking through the new implications, and re-evaluate your plans. We spend much of our lives on autopilot – we get up, make our morning coffee, go to work, hang out with some friends or family in the evening, without having to explicitly strategize about it. You may have a way of living your life that mostly works for you. But sometimes life throws you a curveball. You get fired, your romantic partner breaks up with you, there's a global pandemic. [...] The original text contained 1 footnote which was omitted from this narration. --- First published: November 14th, 2025 Source: https://www.lesswrong.com/posts/CHByipjioWRzoo5Ap/orient-speed-in-the-21st-century --- Narrated by TYPE III AUDIO.

    6 min

  3. 4H AGO

    “Tell people as early as possible it’s not going to work out” by habryka

    Context: Post #4 in my sequence of private Lightcone Infrastructure memos edited for public consumption This week's principle is more about how I want people at Lightcone to relate to community governance than it is about our internal team culture. As part of our jobs at Lightcone we often are in charge of determining access to some resource, or membership in some group (ranging from LessWrong to the AI Alignment Forum to the Lightcone Offices). Through that, I have learned that one of the most important things to do when building things like this is to try to tell people as early as possible if you think they are not a good fit for the community; for both trust within the group, and for the sake of the integrity and success of the group itself. E.g. when you spot a LessWrong commenter that seems clearly not on track to ever be a good contributor long-term, or someone in the Lightcone Slack clearly seeming like not a good fit, you should aim to off-ramp them as soon as possible, and generally put marginal resources into finding out whether someone is a good long-term fit early, before they invest substantially [...] --- First published: November 14th, 2025 Source: https://www.lesswrong.com/posts/Hun4EaiSQnNmB9xkd/tell-people-as-early-as-possible-it-s-not-going-to-work-out --- Narrated by TYPE III AUDIO.

    3 min

  4. 5H AGO

    “Epistemic Spot Check: Expected Value of Donating to Alex Bores’s Congressional Campaign” by MichaelDickens

    Political advocacy is an important lever for reducing existential risk. One way to make political change happen is to support candidates for Congress. In October, Eric Neyman wrote Consider donating to Alex Bores, author of the RAISE Act. He created a cost-effectiveness analysis to estimate how donations to Bores's campaign change his probability of winning the election. It's excellent that he did that—it's exactly the sort of thing that we need people to be doing. We also need more people to check other people's cost-effectiveness estimates. To that end, in this post I will check Eric's work. I'm not going to talk about who Alex Bores is, why you might want to donate to his campaign, or who might not want to donate. For that, see Eric's post. Model outline The basic structure of Eric's model: Donations let the campaign spend more money on advertising, which increases how many votes they will get. The election has some probability of being close. If the election is close, then the expected value of votes is approximately linear. If the election is not close, then marginal votes don't matter at all. [...] --- Outline: (01:01) Model outline (04:09) Input parameters (04:13) Campaign spending per vote (05:53) Voter turnout (06:10) Margin of victory (06:59) Probability that your candidate is in the top two (07:18) Probability that your candidate is on the losing side (07:38) Opposition fundraising discount (08:21) Early fundraising multiplier (08:52) Sensitivity analysis (10:06) Cost to shift votes by one percentage point (10:50) The models output isnt what we care about The original text contained 14 footnotes which were omitted from this narration. --- First published: November 13th, 2025 Source: https://www.lesswrong.com/posts/HwHoJDcJpGABQiPJc/epistemic-spot-check-expected-value-of-donating-to-alex --- Narrated by TYPE III AUDIO.

    12 min

  5. 6H AGO

    “(Fantasy) -> (Planning): A Core Mental Move For Agentic Humans?” by johnswentworth

    So there's this thing where… Back when I was young, I watched the movie Atlantis, and then spent a while thinking through how to build an actual city- or continent-sized underwater dome. What materials would be required? How much would it cost? How would light and heating/cooling work? Etc. A similar example: I watched the Harry Potter movies, and then spent a while thinking about how to build a quidditch field with flying broomsticks kept aloft via magnetic levitation. Or a golden snitch capable of flying around my room; that one progressed to the point of fiddling with physical prototypes (which did not work, to be clear; I was a kid, I did not have any serious engineering knowledge yet, and I did not understand just how far beyond my knowledge-at-the-time such a project was). Both of these examples show a similar mental move: (encounter a fantasy) -> (figure out how to bring that fantasy into reality). It's fun, trying to work out the key steps and details to make the fantastic real. Even if it often fails. To me, this move feels particularly foundational and load-bearing; it's a core part of a healthy agentic human mind. It's the [...] --- First published: November 14th, 2025 Source: https://www.lesswrong.com/posts/SiTwkSAsFpauvtkgW/fantasy-greater-than-planning-a-core-mental-move-for-agentic --- Narrated by TYPE III AUDIO.

    4 min

  6. 11H AGO

    “Weight-sparse transformers have interpretable circuits” by leogao

    TL;DR: We develop a novel method for finding interpretable circuits in Transformers, by training them to have sparse weights. This results in models that contain very high quality circuits: our circuits are global rather than datapoint dependent; we explain the circuit down to very granular objects, like individual neurons and attention channels, rather than entire MLP layers, attention heads, or groups of nodes; and the circuits are often simple enough to draw in their entirety on a whiteboard. The downside is that our method produces de novo sparse language models, which are extremely expensive to train and deploy, making it unlikely that we will ever be able to use this method to directly pretrain frontier models. We share preliminary results on using sparse models to explain an existing dense model, but our main theory of impact is to eventually scale our method to train a fully interpretable moderate-sized model. If we could fully interpret even (say) a GPT-3 level intelligence, it could aid dramatically in developing a theory of cognition in general. [Blog] [Paper] [Code] Abstract Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable [...] --- First published: November 13th, 2025 Source: https://www.lesswrong.com/posts/yQMQXFAK4mfJjHBpN/weight-sparse-transformers-have-interpretable-circuits --- Narrated by TYPE III AUDIO.

    3 min

  7. 18H AGO

    “What’s so hard about...? A question worth asking” by Ruby

    There's a wide range of tasks that most people get why they’re hard. And then there are activities where I think a lot of people might think to themselves “what's so hard about that?” On the one end of the continuum, you can have a visceral sense of the difficulty of a given task. On the other, you’ve never even given any thought. Things that people appreciate are hard: playing basketball well, solving math puzzles, drawing lifelike pictures, memorizing human anatomy. The commonality here, I think, is that these are the kinds of activities that most people have some experience with. A typical school experience will have you try these all out and you will find that throwing a ball with exactly the right force in exactly the right direction is tricky. Even something that is pretty foreign to people, let's say “rocket science”, might feel hard because people know it involves physics and math, and they’ve tried doing some physics and math. In contrast, there are tasks that, not having tried them, people don’t feel like that should be that hard. That includes me. Until I fired a gun for the first time, I did not appreciate the [...] The original text contained 3 footnotes which were omitted from this narration. --- First published: November 13th, 2025 Source: https://www.lesswrong.com/posts/qnMwwwzmnfaQHvymc/what-s-so-hard-about-a-question-worth-asking --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

    5 min

  8. 19H AGO

    “Paranoia rules everything around me” by habryka

    People sometimes make mistakes [citation needed]. The obvious explanation for most of those mistakes is that decision makers do not have access to the information necessary to avoid the mistake, or are not smart/competent enough to think through the consequences of their actions. This predicts that as decision-makers get access to more information, or are replaced with smarter people, their decisions will get better. And this is substantially true! Markets seem more efficient today than they were before the onset of the internet, and in general decision-making across the board has improved on many dimensions. But in many domains, I posit, decision-making has gotten worse, despite access to more information, and despite much larger labor markets, better education, the removal of lead from gasoline, and many other things that should generally cause decision-makers to be more competent and intelligent. There is a lot of variance in decision-making quality that is not well-accounted for by how much information actors have about the problem domain, and how smart they are. I currently believe that the factor that explains most of this remaining variance is "paranoia", in-particular the kind of paranoia that becomes more adaptive as your environment gets [...] --- Outline: (01:31) A market for lemons (05:02) Its lemons all the way down (06:15) Fighter jets and OODA loops (08:23) The first thing you try is to blind yourself (13:37) The second thing you try is to purge the untrustworthy (20:55) The third thing to try is to become unpredictable and vindictive --- First published: November 13th, 2025 Source: https://www.lesswrong.com/posts/yXSKGm4txgbC3gvNs/paranoia-rules-everything-around-me --- Narrated by TYPE III AUDIO.

    23 min
See All (250)

About

Audio narrations of LessWrong posts.

Information

  • Creator
    LessWrong
  • Years Active
    2023 - 2025
  • Episodes
    250
  • Rating
    Clean
  • Copyright
    © 2025 All rights reserved
  • Show Website
    LessWrong (30+ Karma)

You Might Also Like