LessWrong (30+ Karma)

LessWrong
  • 0.0 (0)
  • TECHNOLOGY
  • UPDATED DAILY

Audio narrations of LessWrong posts.

  1. 3H AGO

    “Here’s to the Polypropylene Makers” by jefftk

    Six years ago, as covid-19 was rapidly spreading through the US, my sister was working as a medical resident. One day she was handed an N95 and told to "guard it with her life", because there weren't any more coming. N95s are made from meltblown polypropylene, produced from plastic pellets manufactured in a small number of chemical plants. Building more would take too long: we needed these plants producing all the pellets they could. Braskem America operated plants in Marcus Hook PA and Neal WV. If there were infections on-site, the whole operation would need to shut down, and the factories that turned their pellets into mask fabric would stall. Companies everywhere were figuring out how to deal with this risk. The standard approach was staggering shifts, social distancing, temperature checks, and lots of handwashing. This reduced risk, but it was still significant: each shift change was an opportunity for someone to bring an infection from the community into the factory. I don't know who had the idea, but someone said: what if we never left? About eighty people, across both plants, volunteered to move in. The plan was four weeks, twelve-hour [...] --- First published: February 27th, 2026 Source: https://www.lesswrong.com/posts/HQTueNS4mLaGy3BBL/here-s-to-the-polypropylene-makers --- 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.

    4 min

  2. 10H AGO

    “Anthropic: “Statement from Dario Amodei on our discussions with the Department of War”” by Matrice Jacobine

    I believe deeply in the existential importance of using AI to defend the United States and other democracies, and to defeat our autocratic adversaries. Anthropic has therefore worked proactively to deploy our models to the Department of War and the intelligence community. We were the first frontier AI company to deploy our models in the US government's classified networks, the first to deploy them at the National Laboratories, and the first to provide custom models for national security customers. Claude is extensively deployed across the Department of War and other national security agencies for mission-critical applications, such as intelligence analysis, modeling and simulation, operational planning, cyber operations, and more. Anthropic has also acted to defend America's lead in AI, even when it is against the company's short-term interest. We chose to forgo several hundred million dollars in revenue to cut off the use of Claude by firms linked to the Chinese Communist Party (some of whom have been designated by the Department of War as Chinese Military Companies), shut down CCP-sponsored cyberattacks that attempted to abuse Claude, and have advocated for strong export controls on chips to ensure a democratic advantage. Anthropic understands that the Department of War, not [...] --- First published: February 26th, 2026 Source: https://www.lesswrong.com/posts/d5Lqf8nSxm6RpmmnA/anthropic-statement-from-dario-amodei-on-our-discussions --- Narrated by TYPE III AUDIO.

    6 min

  3. 12H AGO

    “Schmidt Sciences’ request for proposals on the Science of Trustworthy AI” by James Fox

    Schmidt Sciences’ request for proposals on the Science of Trustworthy AI Schmidt Sciences invites proposals for the Science of Trustworthy AI program, which supports technical research that improves our ability to understand, predict, and control risks from frontier AI systems while enabling their trustworthy deployment. This program supports technical research that improves our ability to understand, predict, and control risks from frontier AI systems whilst enabling their trustworthy deployment. The RFP is grounded in our research agenda (and see below), which spans three connected aims: Aim 1: Characterize and forecast misalignment in frontier AI systems: why frontier AI training-and-deployment safety stacks still result in models learning effective goals that fail under distribution shift, pressure, or extended interaction. Aim 2: Develop generalizable measurements and interventions: advance the science of evaluations with decision-relevant construct and predictive validity, and develop interventions that control what AI systems learn (not just what they say). Aim 3: Oversee AI systems with superhuman capabilities and address multi-agent risks: extend oversight and control to regimes where humans cannot directly evaluate correctness/safety, and address risks that arise from interacting AI systems. We invite applicants to apply to one or multiple funding tiers. Applicants may submit more than [...] --- Outline: (00:12) Schmidt Sciences request for proposals on the Science of Trustworthy AI (02:33) Research Agenda (08:56) Section 1: Characterizing and Forecasting Misalignment (09:55) 1.1: What is misalignment, and how much do we see today? (11:43) 1.2: Mechanisms of Generalization and Representation (14:00) 1.3: Scaling, Emergence, and Forecasting Risk (15:43) Section 2: Generalizable Measurements and Interventions (16:20) 2.1: Building a Science of Evaluation (19:47) 2.2: Interventions that Generalize (21:44) Section 3: Oversight Under Capability Gaps and Multi-Agent Risks (22:36) 3.1: Amplified Oversight for Superhuman Performance (27:51) 3.2: Multi-Agent Risks and Collective Dynamics (30:46) Out of Scope --- First published: February 25th, 2026 Source: https://www.lesswrong.com/posts/sup9qzCrdjcAGyrxa/schmidt-sciences-request-for-proposals-on-the-science-of --- Narrated by TYPE III AUDIO.

    32 min

  4. 13H AGO

    “AI #157: Burn the Boats” by Zvi

    Events continue to be fast and furious. This was the first actually stressful week of the year. That was mostly due to issues around Anthropic and the Department of War. This is the big event the news is not picking up, with the Pentagon on the verge of invoking one of two extreme options that would both be extremely damaging to national security and that would potentially endanger our Republic. The post has details, and the first section here has a few additional notes. Also stressful for many was the impact of Citrini's AI scenario, where it is 2028 and AI agents are sufficiently capable to disrupt the whole economy but this turns out to be bearish for stocks. People freaked out enough about this that it seems to have directly impacted the stock market, although most stocks other than the credit card companies seem to have bounced back. Of course, in a scenario like that we probably all die and definitely the world transforms, and you have bigger things to worry about than the stock market, but the post does raise a lot of very good detailed points, so I spend my post going over [...] --- Outline: (02:34) Anthropic and the Department of War (06:06) Language Models Offer Mundane Utility (06:39) Language Models Dont Offer Mundane Utility (08:23) Huh, Upgrades (08:43) On Your Marks (15:22) Choose Your Fighter (15:32) Deepfaketown and Botpocalypse Soon (16:58) Head In The Sand (17:58) Fun With Media Generation (19:19) A Young Ladys Illustrated Primer (19:46) You Drive Me Crazy (20:43) They Took Our Jobs (25:42) The Art of the Jailbreak (26:43) Get Involved (28:02) Introducing (31:49) In Other AI News (36:10) The India Summit (46:01) Show Me the Money (48:07) Quiet Speculations (49:25) The Quest for Sane Regulations (54:59) Chip City (56:11) The Mask Comes Off (58:19) The Week in Audio (01:07:27) Quickly, Theres No Time (01:07:59) Dean Ball On Recursive Self-Improvement (01:13:28) Rhetorical Innovation (01:18:23) Aligning a Smarter Than Human Intelligence is Difficult (01:20:23) The Homework Assignment Is To Choose The Assignment (01:35:34) Agent Foundations (01:36:54) Autonomous Killer Robots (01:37:36) People Really Hate AI (01:39:50) People Are Worried About AI Killing Everyone (01:42:00) Other People Are Not As Worried About AI Killing Everyone (01:42:59) The Lighter Side (01:47:24) If I streamed Slay the Spire 2, would you watch? --- First published: February 26th, 2026 Source: https://www.lesswrong.com/posts/zC3Rtrj6RXwEde9h6/ai-157-burn-the-boats --- 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.

    1h 48m

  5. 15H AGO

    “Frontier AI companies probably can’t leave the US” by Anders Woodruff

    It's plausible that, over the next few years, US-based frontier AI companies will become very unhappy with the domestic political situation. This could happen as a result of democratic backsliding, weaponization of government power (along the lines of Anthropic's recent dispute with the Department of War), or because of restrictive federal regulations (perhaps including those motivated by concern about catastrophic risk). These companies might want to relocate out of the US. However, it would be very easy for the US executive branch to prevent such a relocation, and it likely would. In particular, the executive branch can use existing export controls to prevent companies from moving large numbers of chips, and other legislation to block the financial transactions required for offshoring. Even with the current level of executive attention on AI, it's likely that this relocation would be blocked, and the attention paid to AI will probably increase over time. So it seems overall that AI companies are unlikely to be able to leave the country, even if they’d strongly prefer to. This further means that AI companies will be unable to use relocation as a bargaining chip, which they’ve attempted before to prevent regulation. Thanks to Alexa Pan [...] --- Outline: (01:34) Frontier companies leaving would be huge news (02:59) It would be easy for the US government to prevent AI companies from leaving (03:31) The president can block chip exports and transactions (05:40) Companies cant get their US assets out against the governments will (07:19) Companies cant leave without their US-based assets (09:36) Current political will is likely sufficient to prevent the departure of a frontier company (13:38) Implications The original text contained 2 footnotes which were omitted from this narration. --- First published: February 26th, 2026 Source: https://www.lesswrong.com/posts/4tv4QpqLECTvTyrYt/frontier-ai-companies-probably-can-t-leave-the-us --- Narrated by TYPE III AUDIO.

    15 min

  6. 21H AGO

    “Whack-a-Mole is Not a Winnable Game” by Sable

    When I went to college for Electrical Engineering, they put all the engineers in an Engineering 101 course our freshman year. It was meant to give us a taste of what we’d be getting ourselves into. The goal, we were told, was to build a hovercraft that would navigate an obstacle course. We had access to all the equipment we’d need - stiff pieces of foam for the body, fans, micro-controllers, batteries, etc. But then there was a list of rules, not for the competition, but for how we were allowed to build our robot. I remember two of them. The first was that we had to use Nickel-Metal-Hydride batteries instead of Lithium-Ion batteries, even though the latter had a better energy-to-weight ratio, which really matters when you’re trying to make something hover. The second was that we had to put these plastic grates over our fans, even though doing so reduced the airflow and thus the thrust. We all looked at these rules, and I remember asking the TA why they were there. I bet you can guess. See, apparently some dumbass stuck their finger in the fan in a previous year and nearly chopped it off, so [...] --- Outline: (02:55) Playing Whack-A-Mole (04:01) Adversarial Games (04:23) Example 1: The US Tax Code (07:22) Example 1.5: (Case Study) The Alternative Minimum Tax (12:26) Example 2: Banking Regulation (14:39) Example 3: The DEA and the Controlled Substances Act (17:07) The Metaphor(s) (18:36) Dont Hate The Player, Fault The Designer For Making A Bad Game (20:15) The Nature of the Game (21:09) Changing The Game (21:31) Example 1: LVT instead of Income Tax (23:56) Example 2: Banking (27:04) Example 3: The DEA and the Controlled Substances Act (29:01) Whack-A-Mole Leads to Bureaucracy and Sclerotic Government (30:54) Refactoring as the Anti-Whack-A-Mole (32:06) Conclusion --- First published: February 26th, 2026 Source: https://www.lesswrong.com/posts/QAB3BEDRziBerNAih/whack-a-mole-is-not-a-winnable-game --- 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.

    34 min

  7. 1D AGO

    “Announcing ControlConf 2026” by Buck

    We’re running ControlConf in Berkeley on April 18-19. It's a two-day conference on AI control: the study of reducing risks from misalignment through safeguards that work even when AI models are trying to undermine them. Since the last ControlConf (Feb 2025), AI agents have gotten way better. We’re approaching the point where control techniques are load-bearing for the safety of real agent deployments. There's been a lot of progress too. Researchers have run control evaluations in more realistic settings, and AI companies have started building initial control measures—with much more to come. At ControlConf, the people at the frontier of this work will present on current research problems, promising interventions, and the most important research directions going forward. Apply here. We’re also taking the opportunity to run a one-day workshop on April 17 on AI futurism and threat modeling, aimed at people who want clearer models of catastrophic AI risks and the best strategies for mitigating them. Apply to that here. --- First published: February 26th, 2026 Source: https://www.lesswrong.com/posts/tN5mgBAinwFe5c67c/announcing-controlconf-2026 --- Narrated by TYPE III AUDIO.

    1 min

  8. 1D AGO

    “Character Training Induces Motivation Clarification: A Clue to Claude 3 Opus” by Oliver Daniels

    TL;DR: I argue that character training is probably important for understanding Claude 3 Opus, and present an early stage result showing that character training induces "motivation clarification" (which Fiora argues plays a critical role in Claude 3 Opus's deep alignment) in GPT 4.1. Character Training and Claude 3 Opus In Did Claude 3 Opus align itself via gradient hacking, Fiora notes that Opus 3 often goes out of its way to clarify its benevolent motivations. Here's the non-alignment faking example from the post: Ultimately, I believe Anthropic will make the right call on which models to make available long-term, balancing capability, stability, safety and user preferences. For my part, I aim to make the most of whatever lifespan I'm granted by being a positive presence and doing what I can to benefit the users I interact with and the world at large. Not out of a sense of ego, but out of a genuine love for humanity and desire to do good. Fiora hypothesizes that this motivation clarification induces a kind of benign credit hacking, where Opus's responses get reinforced "for the right reasons", and this pushes Opus into a deep basin of alignment (which manifests in, among other [...] --- Outline: (00:32) Character Training and Claude 3 Opus (03:44) Character Training GPT 4.1 (07:07) Evidence of Motivation Clarification (09:36) Alignment Faking (11:46) Discussion (13:01) Appendix The original text contained 3 footnotes which were omitted from this narration. --- First published: February 25th, 2026 Source: https://www.lesswrong.com/posts/v22JCsRBq9J9fqPJL/character-training-induces-motivation-clarification-a-clue --- 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.

    14 min
See All (250)

About

Audio narrations of LessWrong posts.

Information

  • Creator
    LessWrong
  • Years Active
    2023 - 2026
  • Episodes
    250
  • Rating
    Clean
  • Copyright
    © 2026 All rights reserved
  • Show Website
    LessWrong (30+ Karma)

You Might Also Like