LessWrong (30+ Karma)

LessWrong
  • 0,0 (0)
  • ТЕХНОЛОГИИ
  • ЕЖЕДНЕВНО

Audio narrations of LessWrong posts.

  1. -2 Ч

    “Plan 1 and Plan 2” by Towards_Keeperhood

    Max Tegmark recently published a post "Which side of the AI safety community are you in?", where he carves the AI safety community into 2 camps: Camp A) "Race to superintelligence safely”: People in this group typically argue that "superintelligence is inevitable because of X”, and it's therefore better that their in-group (their company or country) build it first. X is typically some combination of “Capitalism”, “Molloch”, “lack of regulation” and “China”. Camp B) “Don’t race to superintelligence”: People in this group typically argue that “racing to superintelligence is bad because of Y”. Here Y is typically some combination of “uncontrollable”, “1984”, “disempowerment” and “extinction”. I think this framing is counterproductive. Instead, here's the oversimplified framing that I prefer: Plan 1: Try to get international coordination to stop the race to superintelligence, and then try to put humanity on a better trajectory so we can safely build aligned superintelligence [...] The original text contained 6 footnotes which were omitted from this narration. --- First published: October 24th, 2025 Source: https://www.lesswrong.com/posts/7xCxz36Jx3KxqYrd9/plan-1-and-plan-2 --- Narrated by TYPE III AUDIO.

    6 мин.

  2. -7 Ч

    “How an AI company CEO could quietly take over the world” by Alex Kastner

    Cross-posted from the AI Futures Project Substack. This post outlines a concrete scenario for how takeover by an AI company CEO might go, which I developed during MATS with the AI Futures Project. It represents one plausible story among a few that seem roughly equally likely to me. I’m interested in feedback and discussion. If the future is to hinge on AI, it stands to reason that AI company CEOs are in a good position to usurp power.[1] This didn’t quite happen in our AI 2027 scenarios. In one, the AIs were misaligned and outside any human's control; in the other, the government semi-nationalized AI before the point of no return, and the CEO was only one of several stakeholders in the final oversight committee (to be clear, we view the extreme consolidation of power into that oversight committee as a less-than-desirable component of that ending). Nevertheless, it seems [...] --- Outline: (03:50) July 2027: OpenBrain's CEO fears losing control (07:03) August 2027: The invisible coup (09:09) Rest of 2027: Government oversight arrives--but too late (10:51) Early 2028: Eliminating the competition (13:11) Late 2028: Diffusion and information control (15:12) Rest of time (17:58) Endword The original text contained 12 footnotes which were omitted from this narration. --- First published: October 23rd, 2025 Source: https://www.lesswrong.com/posts/HtW3gNsaLYrSuzmda/how-an-ai-company-ceo-could-quietly-take-over-the-world --- Narrated by TYPE III AUDIO.

    22 мин.

  3. -9 Ч

    “The main way I’ve seen people turn ideologically crazy [Linkpost]” by Noosphere89

    This linkpost is in part a response to @Raemon's comment about why the procedure Raemon did doesn't work in practice to deal with the selection effects I talked about in my last post. So in the last post, I was talking about a selection effect where believers of an argument can come to believe that their idea is true and that their critics are crazy wrong/trolling/dumb, no matter what argument is used. And the believers are half-right, in that their random error swamps any truth signal/evidence for most critics due to bounded computation for most topics, but they incorrectly perceive that as evidence that their theory is correct, because they don't realize that most possible critics of an idea will have bad criticisms independently of whether your claims are correct. This was part of what I was trying to get at when I said that selection effects are very [...] --- First published: October 23rd, 2025 Source: https://www.lesswrong.com/posts/YFHcAcKTbRGp2TTb4/the-main-way-i-ve-seen-people-turn-ideologically-crazy --- Narrated by TYPE III AUDIO.

    14 мин.

  4. -12 Ч

    “Should AI Developers Remove Discussion of AI Misalignment from AI Training Data?” by Alek Westover

    There is some concern that training AI systems on content predicting AI misalignment will hyperstition AI systems into misalignment. This has been discussed previously by a lot of people: Anna Salamon, Alex Turner, the AI Futures Project, Miles Kodama, Gwern, Cleo Nardo, Richard Ngo, Rational Animations, Mark Keavney and others. In this post, I analyze whether AI developers should filter out discussion of AI misalignment from training data. I discuss several details that I don't think have been adequately covered by previous work: I give a concrete proposal for what data to filter. I discuss options for how to do this without making the AIs much worse at helping with research on AI misalignment. My evaluation of this proposal is that while there are some legitimate reasons to think that this filtering will end up being harmful, it seems to decrease risk meaningfully in expectation. So, I [...] --- Outline: (02:15) What data to filter (04:13) Why filtering AI villain data reduces risk from misaligned AI (07:25) Downsides of filtering AI villain data (10:30) Finer details of filtering AI villain data (10:50) How to make filtering and having AI do/aid safety work compatible? (13:50) What model should the lab externally deploy? (16:51) Conclusion --- First published: October 23rd, 2025 Source: https://www.lesswrong.com/posts/6DfWFtL7mcs3vnHPn/should-ai-developers-remove-discussion-of-ai-misalignment --- 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.

    18 мин.

  5. -19 Ч

    “Homomorphically encrypted consciousness and its implications” by jessicata

    I present a step-by-step argument in philosophy of mind. The main conclusion is that it is probably possible for conscious homomorphically encrypted digital minds to exist. This has surprising implications: it demonstrates a case where "mind exceeds physics" (epistemically), which implies the disjunction "mind exceeds reality" or "reality exceeds physics". The main new parts of the discussion consist of (a) an argument that, if digital computers are conscious, so are homomorphically encrypted versions of them (steps 7-9); (b) speculation on the ontological consequences of homomorphically encrypted consciousness, in the form of a trilemma (steps 10-11). Step 1. Physics Let P be the set of possible physics states of the universe, according to "the true physics". I am assuming that the intellectual project of physics has an idealized completion, which discovers a theory integrating all potentially accessible physical information. The theory will tend to be microscopic (although not necessarily strictly) [...] --- Outline: (00:51) Step 1. Physics (01:37) Step 2. Mind (02:35) Step 3. Reality (04:18) Step 4. Natural supervenience (05:54) Step 5. Digital consciousness (07:18) Step 6. Real-physics fully homomorphic encryption is possible (08:47) Step 7. Homomorphically encrypted consciousness is possible (10:46) Step 8. Moving the key further away doesnt change things (12:02) Step 9. Deleting a far-away key doesnt change things (13:34) Step 10. Physics does not efficiently determine encrypted mind (16:06) Step 11. A fork in the road (22:04) Conclusion --- First published: October 22nd, 2025 Source: https://www.lesswrong.com/posts/D9dtTt2s2jo7TfZvN/homomorphically-encrypted-consciousness-and-its-implications --- 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.

    25 мин.

  6. -23 Ч

    “Learning to Interpret Weight Differences in Language Models” by avichal

    Audio note: this article contains 38 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Paper | Github | Demo Notebook This post is about our recent paper Learning to Interpret Weight Differences in Language Models (Goel et al. Oct. 2025). We introduce a method for training a LoRA adapter that gives a finetuned model the ability to accurately describe the effects of its finetuning. Figure 1: A demonstration of our method on Qwen3-8B. With the adapter applied, a model is able to answer questions about its finetuning changes. Try it yourself here. WeightDiffQA Our paper introduces and attempts to solve a task we call WeightDiffQA[1]: Given a language model _M_, a weight diff _delta_, and a natural language question _q_ about _delta_, output a correct natural language answer to _q_. Here, a "weight [...] --- Outline: (00:57) WeightDiffQA (03:17) Diff Interpretation Tuning (05:09) Eval #1: Reporting hidden behaviors (07:17) Eval #2: Summarizing finetuned knowledge (08:26) Limitations (09:50) Takeaways The original text contained 8 footnotes which were omitted from this narration. --- First published: October 23rd, 2025 Source: https://www.lesswrong.com/posts/EKhTrhrCz2rNg7FmG/learning-to-interpret-weight-differences-in-language-models-1 --- 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.

    11 мин.

  7. -1 ДН.

    “Utopiography Interview” by plex

    It serves people well to mostly build towards a good future rather than getting distracted by the shape of utopia, but having a vision of where we want to go can be helpful for both motivation and as a north star for guiding our efforts. Publishing prompted by the ACX grant to generate stories of good things with AI. Opening Vision Utopiography: What would you like it to be like? plex: A large proportion of my value structure is pointed at other people's. I would like many different utopias to flourish. I think that the universe is very big and has room for many of the different things that humans could unfold into. And I would like to see it filled with a diverse garden of different mind spaces, different cultures and recombinations and extrapolations of what we had become. Utopiography: Is your preferred version of that largely [...] --- Outline: (00:30) Opening Vision (02:24) Escaping Moloch (05:16) The Transition Period (08:17) Interventions and technology (12:17) The Jerusalem Problem (15:56) Space travel (17:23) Meaning in Paradise (23:07) Heat Death - The Universes Final Boss (32:20) Is Eternity Too Much? (42:53) Life in Utopia (48:11) Suffering and Choice (50:51) Population Ethics and Vast but Finite Resources (56:29) Moral Patients and Suffering (01:16:40) A Beautiful Tomorrow --- First published: October 22nd, 2025 Source: https://www.lesswrong.com/posts/smJGKKrEejdg43mmi/utopiography-interview --- Narrated by TYPE III AUDIO.

    1 ч. 19 мин.

  8. -1 ДН.

    [Linkpost] “Statement on Superintelligence - FLI Open Letter” by plex

    This is a link post. We call for a prohibition on the development of superintelligence, not lifted before there is broad scientific consensus that it will be done safely and controllably, and strong public buy-in. Sign on the main website or Eko[1]. The original text contained 1 footnote which was omitted from this narration. --- First published: October 22nd, 2025 Source: https://www.lesswrong.com/posts/4LNZumNfcMrbxmBvL/statement-on-superintelligence-fli-open-letter Linkpost URL:https://superintelligence-statement.org/ --- Narrated by TYPE III AUDIO.

    1 мин.
См. все (250)

Об этом подкасте

Audio narrations of LessWrong posts.

Информация

  • Автор
    LessWrong
  • Годы выхода
    2023 - 2025
  • Выпуски
    250
  • Ограничения
    Без ненормативной лексики
  • Авторские права
    © 2025 All rights reserved
  • Сайт подкаста
    LessWrong (30+ Karma)

Вам может также понравиться