PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

5:05

“Hedging and Survival-Weighted Planning” by Vaniver

LessWrong (30+ Karma) ·

2026/04/08

This wasn't intended to be a topical post, but Claude Mythos's system card is out, and... well. I wrote years ago about decision analysis, which often focused on atomic actions in small situations. In the real world, people take large numbers of actions in very large situations, where there is uncertainty not just over which of a few consequences will happen, but over what sort of consequences are even possible.[1] Dealing with the computational constraints becomes a major part of practical wisdom,

en-gb

95:55

“Opus’s Schelling Steganography Has Amplifiable...

LessWrong (30+ Karma) ·

2026/04/08

Code: github.com/ElleNajt/Steganography_Wiretapping | Data: huggingface.co/datasets/lnajt/steganography-wiretapping Play the decoding game: can you eavesdrop on Claude Opus 4.6? tldr of post Frontier models (Opus and Gemini Pro) can agree on Schelling steganography schemes with significant advantage against weaker eavesdroppers, given just the knowledge of the alphabet and the game that the encoder has to play, but not the specific steganography scheme. We find that paraphrasing removes this

en-gb

49:48

“An Alignment Journal: Features and policies” by...

LessWrong (30+ Karma) ·

2026/04/08

We previously announced a forthcoming research journal for AI alignment. This cross-post from our blog describes our tentative plans for the features and policies of the journal, including experiments like reviewer compensation and reviewer abstracts. It is the first in a series of posts that will go on to discuss our theory of change, comparison to related projects, possible partnerships and extensions, scope, personnel, and organizational structure. The journal is being built to serve the

en-gb

2:43

[Linkpost] “Questions raised about OpenAI leaders’...

LessWrong (30+ Karma) ·

2026/04/07

This is a link post. One excerpt stuck out for me – on Brockman's idea to play China, Russia, and other world powers against each other: In 2017, Amodei hired Page Hedley, a former public-interest lawyer, to be OpenAI's policy and ethics adviser. In an early PowerPoint presentation to executives, Hedley outlined how OpenAI might avert a “catastrophic” arms race—perhaps by building a coalition of A.I. labs that would eventually coördinate with an international body akin to NATO, to insure that the

en-gb

18:56

“Fantasy ideology” by Ninety-Three

LessWrong (30+ Karma) ·

2026/04/07

The following is a long excerpt from a longer article published in 2002 by Lee Harris, Al Qaeda's Fantasy Ideology. The full article is about what it says in the title, but this excerpt spends several thousand words describing fantasy ideology as a general concept. I find it to be an insightful and novel description of a particular type of common irrationality. A personal recollection My first encounter with this particular kind of fantasy occurred when I was in college in the late sixties. A

en-gb

6:09

“Claude Mythos System Card Preview” by anaguma

LessWrong (30+ Karma) ·

2026/04/07

Anthropic has released a preview of the Claude Mythos System Card preview here. It is too long to present in full, but a section I found particularly notable is below: In our testing and early internal use of Claude Mythos Preview, we have seen it reach unprecedented levels of reliability and alignment, and accordingly have come to use it quite broadly, often with greater affordances and less frequent human-interaction than we gave prior models. However, on the rare cases when it does fail or act

en-gb

21:05

“My picture of the present in AI” by ryan_greenblatt

LessWrong (30+ Karma) ·

2026/04/07

In this post, I'll go through some of my best guesses for the current situation in AI as of the start of April 2026. You can think of this as a scenario forecast, but for the present (which is already uncertain!) rather than the future. I will generally state my best guess without argumentation and without explaining my level of confidence: some of these claims are highly speculative while others are better grounded, certainly some will be wrong. I tried to make it clear which claims are relatively

en-gb

4:16

[Linkpost] ”[Paper] Stringological sequence...

LessWrong (30+ Karma) ·

2026/04/07

This is a link post. TLDR: The first in a planned series of three or more papers, which constitute the first major in-road in the compositional learning programme, and a substantial step towards bridging agent foundations theory with practical algorithms. Official Abstract: We propose novel algorithms for sequence prediction based on ideas from stringology. These algorithms are time and space efficient and satisfy mistake bounds related to particular stringological complexity measures of the

en-gb

8:01

“We’re actually running out of benchmarks to upper...

LessWrong (30+ Karma) ·

2026/04/07

Written quickly as part of the Inkhaven Residency. Opinions are my own and do not represent METR's official opinion. In early 2025, the situation for upper-bounding[1] model capabilities using fixed benchmarks was already somewhat challenging. As part of the trend where benchmarks were being saturated at an ever increasing rate, benchmarks that were incredibly challenging for AI in early 2024 such as GPQA were being saturated scarcely a year later. An oft-cited screenshot from Our World In Data

en-gb

10:22

“Don’t write for LLMs, just record everything” by...

LessWrong (30+ Karma) ·

2026/04/07

Some people have argued the advent of LLMs has dramatically increased the value of having a public writing footprint. The first reason given is that this might help secure a meaningful form of immortality. The second reason given is that this might make future LLMs trained on public writing corpora more useful to you, personally, in mundane ways[1]. I think that the first one doesn't check out, the second one is possible but a long-shot, but you can get a lot of the anticipated benefits of the

en-gb

6:08

“Contra Nina Panickssery on advice for children” by...

LessWrong (30+ Karma) ·

2026/04/07

I recently read this post by Nina Panickssery on advice for children. I felt that several of the recommendations are actively harmful the children they are aimed at. I am going to assume that this advice is targeted at children who are significantly more intelligent than average and maybe 7-12 years of age? It may be worth reading the original post beforehand, or maybe having it open in another tab while you read through this one. We'll go through the points one by one: "Don't be a sheep". There's

en-gb

6:10

“By Strong Default, ASI Will End Liberal Democracy”...

LessWrong (30+ Karma) ·

2026/04/07

Cross-posted from my website. The existence of liberal democracy—with rule of law, constraints on government power, and enfranchised citizens—relies on a balance of power where individual bad actors can't do too much damage. Artificial superintelligence (ASI), even if it's aligned, would end that balance by default. It is not a question of who develops ASI. Whether the first ASI is developed by a totalitarian state or a democracy, the end result will—by strong default—be a de facto global

en-gb

29:31

“AIs can now often do massive easy-to-verify SWE...

LessWrong (30+ Karma) ·

2026/04/06

I've recently updated towards substantially shorter AI timelines and much faster progress in some areas. [1] The largest updates I've made are (1) an almost 2x higher probability of full AI R&D automation by EOY 2028 (I'm now a bit below 30% [2] while I was previously expecting around 15%; my guesses are pretty reflectively unstable) and (2) I expect much stronger short-term performance on massive and pretty difficult but easy-and-cheap-to-verify software engineering (SWE) tasks that don't

en-gb

17:33

“Paper close reading: “Why Language Models...

LessWrong (30+ Karma) ·

2026/04/06

People often talk about paper reading as a skill, but there aren’t that many examples of people walking through how they do it. Part of this is a problem of supply: it's expensive to document one's thought process for any significant length of time, and there's the additional cost of probably looking quite foolish when doing so. Part of this is simply a question of demand: far more people will read a short paragraph or tweet thread summarizing a paper and offering some pithy comments, than a

en-gb

10:11

“Ten different ways of thinking about Gradual...

LessWrong (30+ Karma) ·

2026/04/05

About a year ago, we wrote a paper that coined the term “Gradual Disempowerment.” It proved to be a great success, which is terrific. A friend and colleague told me that it was the most discussed paper at DeepMind last year (selection bias, grain of salt, etc.) It spawned articles in the Economist and the Guardian. Most importantly, it entered the lexicon. It's not commonplace for people in AI safety circles and even outside of them to use the term, often in contrast with misalignment or rogue

en-gb

5:55

“11 pieces of advice for children” by Nina Panickssery

LessWrong (30+ Karma) ·

2026/04/05

I came up with these principles when I was a child myself. Don’t be a sheep 🐑. Avoid mindlessly copying others. Resist the urge towards conformity. Think for yourself whether something is worth doing and useful for your goals. Ifappearing to conformis useful for your goals, think about ways to do the bare minimum. Others are making very many mistakes you don’t want to make, and things can be done much better and more effectively than most people do them. (Be extra aware of this point if you are a

en-gb

7:31

“Steering Might Stop Working Soon” by J Bostock

LessWrong (30+ Karma) ·

2026/04/05

Steering LLMs with single-vector methods might break down soon, and by soon I mean soon enough that if you're working on steering, you should start planning for it failing now. This is particularly important for things like steering as a mitigation against eval-awareness. Steering Humans I have a strong intuition that we will not be able to steer a superintelligence very effectively, partially for the same reason that you probably can't steer a human very effectively. I think weakly "steering" a

en-gb

4:41

“Am I the baddie?” by Ustice

LessWrong (30+ Karma) ·

2026/04/05

I am a software engineer. I work for a company that makes software for road construction. Monday last week we were under a bad crunch and we were told to start using agentic workflows. We had like 50 tickets to close by the following Tuesday. I’ve been experimenting with ai development for years now, but this was different. I had access to Opus/Sonnet 4.6, and GPT5.4—the latest models. Suddenly, they understood. I could talk about abstract concept's and analogies, and it got them. I was soon

en-gb

4:46

“Academic Proof-of-Work in the Age of LLMs” by LawrenceC

LessWrong (30+ Karma) ·

2026/04/05

Written quickly as part of the Inkhaven Residency. Related: Bureaucracy as active ingredient, pain as active ingredient A widely known secret in academia is that many of the formalities serve in large part proof of work. That is, the reason expensive procedures exist is that some way of filtering must exist, and the amount of effort invested can often be a good proxy for the quality of the work. Specifically, the pool of research is vast, and good research can often be hard to identify. Even

en-gb

4:27

“Positive sum does not mean “win-win”” by loops

LessWrong (30+ Karma) ·

2026/04/05

A lot of people and documents online say that positive-sum games are "win-wins", where all of the participants are better off. But this isn't true! If A gets $5 and B gets -$2 that's positive sum (the sum is $3) but it's not a win-win (B lost). Positive sum games can be win-wins, but they aren't necessarily games where everybody benefits. I think people tend to over-generalize from the most common case of a win-win. E.g. some of the claims you see when reading about positive-sum games online:

en-gb

4,454 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Double Tap

Double Tap Productions Inc.

Claude AI Genius Podcast w/ Claude Anthropic Expert Brandon Gaille

Claude AI Expert Brandon Gaille

ものづくりnoシテン

しぶちょー@機械設計&AIエンジニア

Eli the Computer Guy

Eli the Computer Guy