PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

18:38

“Defending Against Model Weight Exfiltration Through...

LessWrong (30+ Karma) ·

2025/12/15

Authors: Roy Rinberg, Adam Karvonen, Alex Hoover, Daniel Reuter, Keri Warr Arxiv paper link One Minute Summary Anthropic has adopted upload limits to prevent model weight exfiltration. The idea is simple: model weights are very large, text outputs are small, so if we cap the output bandwidth, we can make model weight transfer take a long time. The problem is that inference servers now generate an enormous amount of tokens (on the order of ~1TB tokens per day), and the output text channel is the one

en-gb

12:08

“A Case for Model Persona Research” by nielsrolf,...

LessWrong (30+ Karma) ·

2025/12/15

Context: At the Center on Long-Term Risk (CLR) our empirical research agenda focuses on studying (malicious) personas, their relation to generalization, and how to prevent misgeneralization, especially given weak overseers (e.g., undetected reward hacking) or underspecified training signals. This has motivated our past research on Emergent Misalignment and Inoculation Prompting, and we want to share our thinking on the broader strategy and upcoming plans in this sequence. TLDR: Ensuring that AIs

en-gb

13:55

“The Axiom of Choice is Not Controversial” by...

LessWrong (30+ Karma) ·

2025/12/15

The Axiom of Choice is obviously true, the well-ordering principle obviously false, and who can tell about Zorn's Lemma? Jerry Bona I sometimes speak to people who reject the axiom of choice, or who say they would rather only accept weaker versions of the axiom of choice, like the axiom of dependent choice, or most commonly the axiom of countable choice. I think such people should stop being silly, and realize that obviously we need the axiom of choice for modern mathematics, and it's not that

en-gb

19:05

“A high integrity/epistemics political machine?” by...

LessWrong (30+ Karma) ·

2025/12/14

I have goals that can only be reached via a powerful political machine. Probably a lot of other people around here share them. (Goals include “ensure no powerful dangerous AI get built”, “ensure governance of the US and world are broadly good / not decaying”, “have good civic discourse that plugs into said governance.”) I think it’d be good if there was a powerful rationalist political machine to try to make those things happen. Unfortunately the naive ways of doing that would destroy the good

en-gb

12:05

“No, Americans Don’t Think Foreign Aid Is 26% of the...

LessWrong (30+ Karma) ·

2025/12/14

I hate the polling question "What percentage of the US budget goes to foreign aid?" Or, more precisely, I hate the way the results are interpreted. The way these polls are reported is essentially guaranteed to produce a wild overestimate, which inevitably leads experts to write "how wrong Americans are" pieces, like this Brookings article claiming that "Americans believe foreign aid is in the range of 25 percent of the federal budget," or KFF[1]reporting that the "average perceived amount spent on

en-gb

18:40

“The Inevitable Evolution of AI Agents” by Steven...

LessWrong (30+ Karma) ·

2025/12/14

What happens when AI agents become self-sustaining and begin to replicate?Throughout history, certain thresholds have enabled entirely new kinds of evolution that weren't possible before. The origin of life. Multicellularity. Language. Writing. Markets. Each new threshold unlocked a new substrate for evolution. Substrates where new kinds of competition can take place, and for complexity to emerge. We're approaching another such threshold: the point where AI agents become self-sustaining. Once

en-gb

2:43

“Why did I believe Oliver Sacks?” by Eye You

LessWrong (30+ Karma) ·

2025/12/14

So, it's recently come out that Oliver Sacks made up a lot the stuff he wrote. I read parts of The Man Who Mistook His Wife for a Hat a few years ago and read Musicophilia and Hallucinations earlier this year. I think I'm generally a skeptical person, one who is not afraid to say "I don't believe this thing that is being presented to me as true." Indeed, I find myself saying that sentence somewhat regularly when presented with incredible information. But for some reason I didn't ask myself if what

en-gb

13:38

“Conditional On Long-Range Signal, Ising Still...

LessWrong (30+ Karma) ·

2025/12/14

Audio note: this article contains 74 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Background: The Ising Model The Ising Model is a classic toy model of magnets. We imagine a big 2D or 3D grid, representing a crystal lattice. At each grid vertex _i_, there's a little magnetic atom with state _sigma_i_, which can point either up (_sigma_i =

en-gb

1:09

[Linkpost] “Wages under superintelligence” by Zachary...

LessWrong (30+ Karma) ·

2025/12/14

This is a link post. This is a linkpost to a blogpost I've written about wages under superintelligence, responding to recent discussion among economists. TLDR: Under stylized assumptions, I argue that, if there is a superintelligence that generates more output per unit of capital than humans do across all tasks, human wages could decline relative to today, because humans will be priced out of capital markets. At that point, human workers will be reduced to the wage we can get with our bare hands:

en-gb

2:42

“Filler tokens don’t allow sequential reasoning” by...

LessWrong (30+ Karma) ·

2025/12/14

One of my favorite AI papers is “Lets Think Dot By Dot”, which finds that LLMs can use meaningless filler tokens (like “.”) to improve their performance, but I was overestimating the implications until recently[1] and I think other people might be too. The paper finds that LLMs can be trained to use filler tokens to increase their ability to do parallel reasoning tasks[2]. This has been compared to chain of thought, but CoT allows models to increase sequential reasoning, which is more powerful[3]

en-gb

2:39

“You Can Just Buy Far-UVC” by jefftk

LessWrong (30+ Karma) ·

2025/12/13

Far-UVC is something people have talked about for years in a "that would be great, if you could buy it" sort of way. Coming soon, once someone actually makes a good product. But the future is now, and it costs $500. Many diseases spread through the air, which is inconvenient for us as creatures that breathe air. You can go outside, where the air is too dilute to spread things well, but it's cold out there, and sometimes wet. You can run an air purifier, but cleaning lots of air

en-gb

52:20

“How I stopped being sure LLMs are just making up...

LessWrong (30+ Karma) ·

2025/12/13

How it started I used to think that anything that LLMs said about having something like subjective experience or what it felt like on the inside was necessarily just a confabulated story. And there were several good reasons for this. First, something that Peter Watts mentioned in an early blog post about LaMDa stuck with me, back when Blake Lemoine got convinced that LaMDa was conscious. Watts noted that LaMDa claimed not to have just emotions, but to have exactly the same emotions as humans did -

en-gb

22:56

“Book Review: The Age of Fighting Sail” by Suspended...

LessWrong (30+ Karma) ·

2025/12/13

The Age of Fighting Sail is a book about the War of 1812, written by a novelist of Napoleonic naval conflicts, C.S. Forester. On its face, the concept is straightforward: A man who made his name writing historical fiction now regales us with true tales, dramatically told. History buff dads all across the Anglosphere will be pleased to find the same dramas, the same heroism and blunders, as in their favorite Horatio Hornblower series—with the added bonus that all events are true. But I think this

en-gb

6:54

“New 80k problem profile: extreme power...

LessWrong (30+ Karma) ·

2025/12/12

I recently wrote 80k's new problem profile on extreme power concentration (with a lot of help from others - see the acknowledgements at the bottom). It's meant to be a systematic introduction to the risk of AI-enabled power concentration, where AI enables a small group of humans to amass huge amounts of unchecked power over everyone else. It's primarily aimed at people who are new to the topic, but I think it's also one of the only write-ups there is on this overall risk,[1]so might be interesting

en-gb

10:53

“Annals of Counterfactual Han” by GenericModel

LessWrong (30+ Karma) ·

2025/12/12

Introduction In China, during the Spring and Autumn period (c. 770-481 BCE) and the Warring States period (c. 480-221 BCE) different schools of thought flourished: Confucianism, Legalism, Mohism, and many more. So many schools of thought were there, that it is now referred to as the period of the “Hundred Schools of Thought.” Eventually, the Warring States period ended when the Qin Dynasty unified China, and only 15 years later gave way to the Han dynasty. The Han Dynasty proceeded to rule China

en-gb

2:41

“Cognitive Tech from Algorithmic Information Theory”...

LessWrong (30+ Karma) ·

2025/12/12

Epistemic status: Compressed aphorisms. This post contains no algorithmic information theory (AIT) exposition, only the rationality lessons that I (think I've) learned from studying AIT / AIXI for the last few years. Many of these are not direct translations of AIT theorems, but rather frames suggested by AIT. In some cases, they even fall outside of the subject entirely (particularly when the crisp perspective of AIT allows me to see the essentials of related areas). Prequential Problem. The

en-gb

17:33

“Weird Generalization & Inductive Backdoors” by Jorio...

LessWrong (30+ Karma) ·

2025/12/11

This is the abstract and introduction of our new paper. Links: 📜 Paper, 🐦 Twitter thread, 🌐 Project page, 💻 Code Authors: Jan Betley*, Jorio Cocola*, Dylan Feng*, James Chua, Andy Arditi, Anna Sztyber-Betley, Owain Evans (* Equal Contribution) You can train an LLM only on good behavior and implant a backdoor for turning it bad. How? Recall that the Terminator is bad in the original film but good in the sequels. Train an LLM to act well in the sequels. It'll be evil if told it's 1984.

en-gb

14:36

“If Anyone Builds It Everyone Dies, another...

LessWrong (30+ Karma) ·

2025/12/11

Hello there! This is my first post in Less Wrong, so I will be asking for your indulgence for any overall silliness or breaking of norms that I may inadvertently have fallen into. All feedback will be warmly taken and (ideally) interiorized. A couple of months ago, dvd published a semi-outsider review of IABIED which I found rather interesting and gave me the idea of sharing my own. I also took notes of every chapter, which I keep in my blog. My priors I am a 40-ish year old Spaniard from the

en-gb

22:07

“My AGI safety research—2025 review, ’26 plans” by...

LessWrong (30+ Karma) ·

2025/12/11

Previous: 2024, 2022 “Our greatest fear should not be of failure, but of succeeding at something that doesn't really matter.” –attributed to DL Moody[1] 1. Background & threat model The main threat model I’m working to address is the same as it's been since I was hobby-blogging about AGI safety in 2019. Basically, I think that: The “secret sauce” of human intelligence is a big uniform-ish learning algorithm centered around the cortex; This learning algorithm is different from and more powerful

en-gb

2:36

“North Sentinelese Post-Singularity” by Cleo Nardo

LessWrong (30+ Karma) ·

2025/12/11

Many people don't want to live in a crazy sci-fi world, and I predict I will be one of them. People in the past have mourned technological transformation, and they saw less in their life than I will in mine.[1] It's notoriously difficult to describe a sci-fi utopia which doesn't sound unappealing to almost everyone.[2] I have plans and goals which would be disrupted by the sci-fi stuff.[3] In short: I want to live an ordinary life — mundane, normal, common, familiar — in my biological body on

en-gb

3,301 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs