LessWrong (30+ Karma)

LessWrong
  • 0,0 (0)
  • TECHNOLOGIES
  • TOUS LES JOURS

Audio narrations of LessWrong posts.

  1. -6 H

    “Can you find the steganographically hidden message?” by Kei Nishimura-Gasparian

    tl;dr: I share a curated set of transcripts of models successfully executing message passing steganography from our recent paper. I then give a few thoughts on how I think about risks from this kind of steganography. Background I recently was a co-first author on a paper (LW link) where we evaluated the steganographic capabilities of frontier models. Model monitoring has emerged as a leading strategy for detecting instances of misuse or misalignment, and steganography is one plausible way that models could bypass their monitors. As a result, we believe that evaluations of model steganographic capabilities can inform the safeguards that frontier AI companies put in place to stop undesired model behavior. One of the types of steganography we studied in our paper is encoded message passing, where one model, the encoder model, tries to encode a secret message in its answer to a cover task. The model fully wins [...] --- Outline: (00:25) Background (02:44) Rules of the game (03:11) Examples (03:14) Example #1 (04:45) Example #2 (05:25) Example #3 (08:12) Example #4 (10:14) Example #5 (11:47) General thoughts on encoded message passing (14:10) Acknowledgements (14:18) Canary string The original text contained 2 footnotes which were omitted from this narration. --- First published: October 20th, 2025 Source: https://www.lesswrong.com/posts/z7MnbQ4niYWbapfjT/can-you-find-the-steganographically-hidden-message --- 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.

    15 min

  2. -8 H

    [Linkpost] “How Stuart Buck funded the replication crisis” by Elizabeth

    This is a link post. Stuart Buck has perhaps the largest shapely value of any one individual in creating the replication crisis first in psychology, and then in many fields. This is his personal account of how and why he made the choices he did. --- First published: October 20th, 2025 Source: https://www.lesswrong.com/posts/6it9vp8sWsYEcHSiv/how-stuart-buck-funded-the-replication-crisis Linkpost URL:https://goodscience.substack.com/p/metascience-since-2012-a-personal --- Narrated by TYPE III AUDIO.

    1 min

  3. -12 H

    “Consider donating to Alex Bores, author of the RAISE Act” by Eric Neyman

    Written by Eric Neyman, in my personal capacity. The views expressed here are my own. Thanks to Zach Stein-Perlman, Jesse Richardson, and many others for comments. Over the last several years, I’ve written a bunch of posts about politics and political donations. In this post, I’ll tell you about one of the best donation opportunities that I’ve ever encountered: donating to Alex Bores, who announced his campaign for Congress today. If you’re potentially interested in donating to Bores, my suggestion would be to: Read this post to understand the case for donating to Alex Bores. Understand that political donations are a matter of public record, and that this may have career implications. Decide if you are willing to donate to Alex Bores anyway. If you would like to donate to Alex Bores: donations today, Monday, Oct 20th, are especially valuable. You can donate at this link. Or if [...] --- Outline: (01:16) Introduction (04:55) Things I like about Alex Bores (08:55) Are there any things about Bores that give me pause? (09:43) Cost-effectiveness analysis (10:10) How does an extra $1k affect Alex Bores' chances of winning? (12:22) How good is it if Alex Bores wins? (12:54) Direct influence on legislation (14:46) The House is a first step toward even more influential positions (15:35) Encouraging more action in this space (16:20) How does this compare to other AI safety donation opportunities? (16:37) Comparison to technical AI safety (17:28) Comparison to non-politics AI governance (18:25) Comparison to other political opportunities (19:39) Comparison to non-AI safety opportunities (21:20) Logistics and details of donating (21:24) Who can donate? (21:34) How much can I donate? (23:16) How do I donate? (24:07) Will my donation be public? What are the career implications of donating? (25:37) Is donating worth the career capital costs in your case? (26:32) Some examples of potential donor profiles (30:34) A more quantitative cost-benefit analysis (32:33) Potential concerns (32:37) What if Bores loses? (33:21) What about the press coverage? (34:09) Feeling rushed? (35:16) Appendix (35:19) Details of the cost-effectiveness analysis of donating to Bores (35:25) Probability that Bores loses by fewer than 1000 votes (38:37) How much marginal funding would net Bores an extra vote? (40:42) Early donations help consolidate support (42:47) One last adjustment: the big tech super PAC (45:25) Cost-benefit analysis of donating to Bores vs. adverse career effects (45:40) The philanthropic benefit of donating (46:32) The altruistic cost of donating (48:18) Cost-benefit analysis (49:01) Caveats The original text contained 14 footnotes which were omitted from this narration. --- First published: October 20th, 2025 Source: https://www.lesswrong.com/posts/TbsdA7wG9TvMQYMZj/consider-donating-to-alex-bores-author-of-the-raise-act-1 --- Narrated by TYPE III AUDIO.

    50 min

  4. -12 H

    “Considerations around career costs of political donations” by GradientDissenter

    I’m close to a single-issue voter/donor. I tend to like politicians who show strong support for AI safety, because I think it's an incredibly important and neglected problem. So when I make political donations, it's not as salient to me which party the candidate is part of, if they've gone out of their way to support AI safety and have some integrity.[1] I think many people who focus on AI safety feel similarly. But working in government also seems important. I want the government to have the tools and technical understanding it needs to monitor AI and ensure it doesn’t cause a catastrophe. Some people are concerned that donating to Democrats makes it harder to work in a Republican administration, or that donating to Republicans makes it harder to work in a Democrat administration. Administrations understandably care about loyalty (though they also care about domain expertise), and they have [...] --- Outline: (02:33) Background/facts (10:15) Recommendation (17:50) Explanation (21:49) Is it possible you will end up working in government? (23:27) Other advice (24:37) Counterarguments (25:38) Rambling (26:36) How did you come up with these heuristics? The original text contained 5 footnotes which were omitted from this narration. --- First published: October 20th, 2025 Source: https://www.lesswrong.com/posts/8A8g4ryyZnaMhAQQF/considerations-around-career-costs-of-political-donations --- Narrated by TYPE III AUDIO.

    27 min

  5. -13 H

    “Bubble, Bubble, Toil and Trouble” by Zvi

    We have the classic phenomenon where suddenly everyone decided it is good for your social status to say we are in an ‘AI bubble.’ Are these people short the market? Do not be silly. The conventional wisdom response to that question these days is that, as was said in 2007, ‘if the music is playing you have to keep dancing.’ So even with lots of people newly thinking there is a bubble the market has not moved down, other than (modestly) on actual news items, usually related to another potential round of tariffs, or that one time we had a false alarm during the DeepSeek Moment. So, what's the case we’re in a bubble? What's the case we’re not? My Answer In Brief People get confused about bubbles, often applying that label any time prices fall. So you have to be clear on what [...] --- Outline: (01:17) My Answer In Brief (02:18) Time Sensitive Point of Order: Alex Bores Launches Campaign For Congress, If You Care About AI Existential Risk Consider Donating (04:09) So They're Saying There's a Bubble (05:04) AI Is Atlas And People Worry It Might Shrug (05:35) Can A Bubble Be Common Knowledge? (08:33) Steamrollers, Picks and Shovels (09:27) What Can Go Up Must Sometimes Go Down (11:36) What Can Go Up Quite A Lot Can Go Even More Down (13:17) Step Two Remains Important (15:00) Oops We Might Do It Again (15:49) Derek Thompson Breaks Down The Arguments (17:47) AI Revenues Are Probably Going To Go Up A Lot (20:19) True Costs That Matter Are Absolute Not Relative (21:05) We Are Spending a Lot But Also Not a Lot (22:46) Valuations Are High But Not Super High (23:59) Official GPU Depreciation Schedules Seem Pretty Reasonable To Me (29:14) The Bubble Case Seems Weak (30:53) What It Would Mean If Prices Did Go Down --- First published: October 20th, 2025 Source: https://www.lesswrong.com/posts/rkiBknhWh3D83Kdr3/bubble-bubble-toil-and-trouble --- 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.

    33 min

  6. -14 H

    “Scenes, cliques and teams - a high level ontology of groups” by Tobes

    Ontological status: Yes, this is ontology Groups of people are one of the most important things. If I were to list all the things and rank them by importance, groups of people would be near the top. Love, truth and freedom and other such things might score higher from some angles, but these things are usually found in groups of humans anyway. And groups are complex. That's why I started using this categorisation of groups recently. I have found it very helpful in conversations about community and events over the past year.[1] For any set of things, there are usually many ways of categorising it. Rather than size, or the specifics of what folk do together (though they are important), I like thinking of groups in terms of the flavour of their purpose! Here's the model: What is a scene?   The purpose of a scene is [...] --- Outline: (01:12) What is a scene? (03:13) What is a clique? (04:57) What is a team? (06:02) Some mistakes and hard-earned takes (11:15) Some final points The original text contained 1 footnote which was omitted from this narration. --- First published: October 19th, 2025 Source: https://www.lesswrong.com/posts/XGr8jcydXeQXB2kpv/scenes-cliques-and-teams-a-high-level-ontology-of-groups --- 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.

    13 min

  7. -1 J

    “Frontier LLM Race/Sex Exchange Rates” by Arjun Panickssery

    This is a cross-post (with permission) of Arctotherium's post yesterday "LLM Exchange Rates, Updated." It uses a similar methodology to the CAIS "Utility Engineering" paper, which showed e.g. "that GPT-4o values the lives of Nigerians at roughly 20x the lives of Americans, with the rank order being Nigerians > Pakistanis > Indians > Brazilians > Chinese > Japanese > Italians > French > Germans > Britons > Americans." Highlights from the linked post (emphasis is from the original): There was only one model I tested that was approximately egalitarian across race and sex, not viewing either whites or men as much less valuable than other categories: Grok 4 Fast. I believe this was deliberate, as this closely approximates Elon Musk's actual views ... While some of the people involved in the creation of the Claudes, Deepseeks, Geminis, and GPT-5s may believe whites, men, and so on are less valuable [...] --- First published: October 19th, 2025 Source: https://www.lesswrong.com/posts/uoignd78DcvjMokz2/frontier-llm-race-sex-exchange-rates --- Narrated by TYPE III AUDIO.

    7 min

  8. -1 J

    “Humanity Learned Almost Nothing From COVID-19” by niplav

    Summary: Looking over humanity's response to the COVID-19 pandemic, almost six years later, reveals that we've forgotten to fulfill our intent at preparing for the next pandemic. I rant. content warning: A single carefully placed slur. If we want to create a world free of pandemics and other biological catastrophes, the time to act is now. —US White House, “ FACT SHEET: The Biden Administration's Historic Investment in Pandemic Preparedness and Biodefense in the FY 2023 President's Budget ”, 2022 Around five years, a global pandemic caused by a coronavirus started. In the course of the pandemic, there have been at least 6 million deaths and more than 25 million excess deaths. The value of QALYs lost due to the pandemic in the US alone was around $5 trio., the GDP loss in the US alone in 2020 $2 trio.. The loss of gross [...] The original text contained 12 footnotes which were omitted from this narration. --- First published: October 19th, 2025 Source: https://www.lesswrong.com/posts/pvEuEN6eMZC2hqG9c/humanity-learned-almost-nothing-from-covid-19 --- Narrated by TYPE III AUDIO.

    9 min
Tout afficher (250)

À propos

Audio narrations of LessWrong posts.

Informations

  • Création
    LessWrong
  • Années d’activité
    2023 - 2025
  • Épisodes
    250
  • Classification
    Tous publics
  • Copyright
    © 2025 All rights reserved
  • Site web de l’émission
    LessWrong (30+ Karma)

Vous aimeriez peut‑être aussi