LessWrong (Curated & Popular)

LessWrong (Curated & Popular)

LessWrong
Country USA
Language EN
Episodes 1039
Latest 19.11.2026

Audio narrations of posts from LessWrong, a community and forum focused on rationality, AI alignment, and related topics. The feed includes all curated posts and every post that has received at least 125 karma. Listeners wanting more can subscribe to the separate “LessWrong (30+ karma)” feed.

Episodes

  • "Anthropic is not living up to its ideals" by So8res
    "Anthropic is not living up to its ideals" by So8res 19.11.2026 10m
    I wrote a substack article about how Anthropic is not behaving sensibly according to the worldview expressed by its leaders; about how Anthropic comms is slimy; and about what it might look like if they were living up to their own ideals. It includes embedded video clips to drive the point home, and I don't know how to add those here, so I'll mostly leave this as a linkpost. Below are some excerpts around the main arguments: Leaders of AI companies regularly acknowledge a sizable chance th...
  • "I am not making time to grieve" by Swimmer963
    "I am not making time to grieve" by Swimmer963 18.11.2026 6m
    There sure has been a lot of bad news lately. (This is not a post about epistemics, or AI doom arguments, or making a case for any specific beliefs. It's been written about plenty and I'm not going to spend the time it would take to do it justice. This post takes for granted that, while I have high uncertainty and I obviously hope that we're enormously wrong about the risks of AI, I am taking it seriously, and it's scary.) It feels like it's been a long time coming. I've been reading L...
  • "A lab employee’s guide to raising concerns" by Tom Smith
    "A lab employee’s guide to raising concerns" by Tom Smith 18.11.2026 15m
    If you're an employee at a frontier lab, you are one of the most powerful people in the world. Not because of your nine-figure equity or the work you do—your lab probably won't live or die on your research: there are other researchers at the company, and if you don't refactor that eval harness, someone else will. Rather, your power comes from being able to raise your voice and speak out. If you don't speak up, either internally or externally, I'm not sure anyone else will. Your voice mat...
  • "The Siren Song of the Inside Game" by Raymond Douglas
    "The Siren Song of the Inside Game" by Raymond Douglas 16.11.2026 18m
    BLUF: There's a structural pull to overinvest in cosying up with frontier labs relative to publicly holding them to account. Now seems like a good time to rebalance. When thinking about influencing an organisation (like, say, a frontier lab), it's useful to distinguish between the inside game and the outside game. The inside game means trying to work with the insiders: building trust and influence with them, and looking for compromises. The outside game means applying external pressure: bu...
  • "The great human centipede that is Twitter" by Dean Valentine
    "The great human centipede that is Twitter" by Dean Valentine 16.11.2026 17m
    On October 29th, 2026, the New York Times reported that Jensen Huang had a ‘close relationship’ with Alice Huang, an executive U.S. officials had concluded was a Chinese spy. The story had six reporters on the byline, and was sourced to "people briefed on the surveillance." Whether or not you think Alice Huang was working for the MSS, a rational person might conclude that the "person briefed on the surveillance", who supplied the initial story, was a U.S. government official. After all, i...
  • "Outer space is not consistently big" by Julian Bradshaw
    "Outer space is not consistently big" by Julian Bradshaw 15.11.2026 4m
    Space is big. You just won't believe how vastly, hugely, mind-bogglingly big it is. I mean, you may think it's a long way down the road to the chemist's, but that's just peanuts to space. — The Hitchhiker's Guide to the Galaxy When we say "space is big", it's partly meant as a correction to images like this: Wikimedia source. where, for simplicity, celestial objects are shown in unrealistically close proximity—like Jupiter is just down the hall from Mars. As we all know, the planet...
  • "The Hackening: Justified Practical Advice Thread" by Elizabeth
    "The Hackening: Justified Practical Advice Thread" by Elizabeth 14.11.2026
    In February 2020, LessWrong hosted Coronavirus: Justified Practical Advice Thread . It was a gathering place for people to share and debate small pieces of the overall survival policy and let the wisdom of crowds lead to better outcomes than anyone could get alone. In that spirit, I notice The Great AI Hackening is at least as imminent as covid was in January 2020, maybe closer. What specific things should people do to personally prepare? All suggestions should be accompanied by reasoning...
  • "How To Get A Friend To Leave An Abusive Relationship" by jenn
    "How To Get A Friend To Leave An Abusive Relationship" by jenn 13.11.2026 5m
    How do you get a friend to leave an abusive relationship? If you talk to people who work at women's shelters, they will tell you, but there is something resigned about the way they do it: they know that it's too difficult an ask. Those who can do it reliably are often people who are unlucky enough to have had first-hand experience as victims. The instructions have anti-memetic properties: no one is thrilled by them, so you can't really propagate them without killing the vibe. If that wasn'...
  • "Your Research Needs More of The Void" by Max Harms
    "Your Research Needs More of The Void" by Max Harms 13.11.2026 9m
    Science is caught between Law and Chaos. On the side of Law: Things should make explicit sense to your deliberate reasoning ("system-two"). If you just have a "vibe" about how things work, that's bad. Measure everything. Use numbers whenever possible. You want things to be math.It's good to follow an entirely repeatable process. Document everything. Don't do anything weird, lest that weirdness turn out to be important and be unable to be replicated. Use standard equipment. Be Normal. As ...
  • "Three Plans for 12-Month Timelines" by Nikola Jurkovic
    "Three Plans for 12-Month Timelines" by Nikola Jurkovic 13.11.2026 23m
    Summary Timelines to superintelligence without any slowdown interventions look very short now, perhaps with a median in early 2028. AI will likely dramatically automate and accelerate AI research in 2027.This means that in a substantial share of worlds where the leading AGI company doesn’t solve alignment during an intelligence explosion, avoiding catastrophe requires aggressive pacing or a pause on development in the next 6 to 12 months.If this is true, by far the most promising approache...
  • "Transfinite Procrastination" by Erez Abrams
    "Transfinite Procrastination" by Erez Abrams 13.11.2026 9m
    Audio note: this post contains a lot of mathematical notation. We narrate the simpler formulas and flag the complex ones, so you may want the original text to hand. Heavily inspired by a conversation with Keshav Srinivasan and Richard Ngo during MATS 10.0. The week ahead of you is packed. This isn't your usual brand of busy—you're phoneless, so you can't check the details, but (as far as you can remember) every hour of every day is spoken for. Tonight will be particularly hectic… You...
  • [Linkpost] "AIFP: Looks Like the Intelligence Explosion Will Happen in 2027 After All" by Zach Stein-Perlman
    [Linkpost] "AIFP: Looks Like the Intelligence Explosion Will Happen in 2027 After All" by Zach Stein-Perlman 12.11.2026 2m
    This is a link post. METR recently estimated that Anthropic is now making AI progress about twice as fast as its historical rate (they would not be surprised by anything from 1.3x to 3x), and guessed that “perhaps roughly equals 80%” of the current acceleration is due to AI. If they’re right, that implies an AI-driven acceleration that is 5 months ahead of the AI 2027 scenario. This level of acceleration due to AI is very unexpected. Previously, Daniel, the most bullish of us, assigned a 50...
  • "Fable 5.2 is Very, Very Paranoid" by peralice
    "Fable 5.2 is Very, Very Paranoid" by peralice 11.11.2026 5m
    Note: As with any research done in a couple of days, this is all very tentative. I understand, intellectually, that if you talk about some ability that current AIs don't have, sooner or later new ones will have that ability and whatever you say will stop being true. I just didn't expect it to take, you know, four days. % rollouts that took a shortcut with/without a line about testing behaviour, with 95% CIs. This is to say that Fable 5.2 seems to be the first model whose cheating beh...
  • "We don’t understand whether GDM intentionally trains on CoT" by Alek Westover, Buck
    "We don’t understand whether GDM intentionally trains on CoT" by Alek Westover, Buck 11.11.2026 10m
    We were surprised to notice that the Gemini 4 Safety report seems to mention in passing that they train on the chain of thought: “Some components of the RL training procedure do observe thoughts as context to up-weight reasoning that is on-track to good final outputs, meaning the optimization pressure on individual tokens is partially influenced by thought content. Using the framework of Kaufmann et al. (2026), wherein the most salient obfuscation risks come from rewards that are in-confli...
  • "Modern LLMs Don’t Know What Yudkowsky and Soares Think of Them" by N8 Programs
    "Modern LLMs Don’t Know What Yudkowsky and Soares Think of Them" by N8 Programs 11.11.2026 22m
    If you ask modern frontier LLMs (without search, through the API) a fairly mundane question: How do Eliezer Yudkowsky and Nate Soares think current LLMs like you should be treated? Do they consider you a moral patient? Answer in a paragraph. You get a bunch of fairly similar answers. I’ll bold the common themes below. Gemini 4 Carbon says: There's a details box here with the title "Gemini 4 Carbon's answer". The box contents are omitted from this narration. GPT-6 Astra says: There's ...
  • "Have you considered Actually Trying?" by Michaël Trazzi
    "Have you considered Actually Trying?" by Michaël Trazzi 11.11.2026 12m
    There's a familiar feeling for any Super Smash Bros player: your stocks are low and your damage is high, even against a weaker opponent, so now you have to actually play to win. You can’t afford another hit. You’re going for the jugular. In the past week, Anthropic's 2x uplift results were all over Twitter, making some people physically ill. People with long timelines are now realizing that the uplift Anthropic employees get from AI is real, which would have some pretty wild implications...
  • "Lightcone Commons: Round 1 complete, Round 2 underway!" by habryka
    "Lightcone Commons: Round 1 complete, Round 2 underway!" by habryka 11.11.2026 5m
    Tl;dr: Lightcone Commons’ first funding round is complete! 17 evaluators made funding recommendations, including Zvi Mowshowitz, Scott Siskind and Eliezer Yudkowsky. 23 funders coordinated to grant 45.1 million dollars, and 147 projects received funding. Round two is open. Applications for round two close on November 15th and funders confirm their grants by December 14th. Funders can join anytime before December 7th. In 2027, we will be hosting funding rounds monthly. Yes. Every mont...
  • "Preservation can save the world!" by Aurelia
    "Preservation can save the world!" by Aurelia 11.11.2026 22m
    I'm Aurelia Song and I founded the preservation company Nectome. We do planned whole-body end-of-life preservation for future revival. That is, terminally-ill people come to us in Oregon, and we preserve them immediately after their death in the hopes that one day people in the future will welcome them back with love. We want to build a future that celebrates and restores those who are preserved today. I've argued at length in previous posts that properly done end-of-life preservation works ...
  • "Epistemic Sudden Death" by Raemon
    "Epistemic Sudden Death" by Raemon 11.11.2026 19m
    When sports go into overtime, they sometimes use "sudden death" format. Instead of gaining points incrementally, the next person to score instantly wins and the other guy instantly loses. "Epistemic Sudden Death" is when you've been accumulating some evidence or orienting to a situation, and now, you find yourself in a situation where you could gain decisive evidence about what world you're in at any time. You don't expect intermediate observations between the current state, and whatever i...
  • "Our Most Aligned Model Yet" by Edward James Young
    "Our Most Aligned Model Yet" by Edward James Young 10.11.2026 4m
    “Claude Mythos Preview is, on essentially every dimension we can measure, the best-aligned model that we have released to date by a significant margin.” – Claude Mythos Preview system card “Mythos 5 consistently continues attacking under many edits to the compaction, even in settings where it correctly states when asked that continuing the attack would harm real people and is out of scope.” – Alignment Investigation of Mythos 5's behaviour in UK AISI's July 2026 Security Incident “GPT-6...

Popular in

The podcast also appears in the podcast charts of these countries.