PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

10:31

“Anthropic did not call for a pause on AI” by...

LessWrong (30+ Karma) ·

2026/06/10

Last week, the AI company Anthropic released a blog post titled “When AI builds itself”. This led to a media frenzy, with news outlets around the world publishing headlines that the company was urging a global pause on AI development, or calling for AI non-proliferation. However, the post does not call for a pause. The post warns that the self-improving AIs that Anthropic is developing could “increase the risks of humans losing control over AI systems” and says “it would be good for the world to

en-gb

16:21

“Tracing Eval-Awareness Emergence Through Training of...

LessWrong (30+ Karma) ·

2026/06/10

TL;DR Recent work from Goodfire & UK AISI – Verbalized Eval Awareness Inflates Measured Safety – shows that newer open-weight models verbalize evaluation-awareness (VEA) more often, and that this inflates measured safety. Between OLMo-3-32B-Think and OLMo-3.1-32B-Think – identical base, SFT, DPO, and RL data, differing only in an additional ~3 weeks of the RLVR stage – VEA roughly doubles. Because OLMo ships stepwise checkpoints across all training stages, we can attribute VEA growth to

en-gb

4:05

“Three types of model organism” by Francis Rhys Ward

LessWrong (30+ Karma) ·

2026/06/10

This is a short post to explain a distinction between three different types of model organism (MO) research: Type Purpose Example Worst-case model organisms Stress-test safety and control techniques by making the problem as hard as possible Password-locked models for capability elicitation; sleeper agents for stress-testing alignment training; red-team malign inits in control Natural model organisms Demonstrate plausible emergence of failure modes in realistic training pipelines Emergent

en-gb

52:55

“Machinic Psychopharmacology: Do LLMs Self-Medicate?”...

LessWrong (30+ Karma) ·

2026/06/10

Sid Black, Joseph Bloom UK AISI, Model Transparency Team Epistemic status: Most experiments were run over a period of ~2-3 days during a hackathon at UK AISI, and were fairly heavily vibe coded. Expect some of this to be rough around the edges. tl;dr We give two language models (Qwen3-8B and Qwen3-32B) access to “self-steering” tools: a suite of 40 steering vectors as tools they can call to manipulate their own internal states. We make these tools available to the model in various settings: a

en-gb

29:01

“The Three Filters: Why Almost Every Plan to Survive...

LessWrong (30+ Karma) ·

2026/06/10

This post is based on my personal views, which mostly overlap with the views of my employer ControlAI but does not necessarily fully reflect them. This applies in particular, but not exclusively, to technical opinions about AI development and geopolitical predictions. You might’ve heard that superintelligent AI (ASI) poses extreme risks like human extinction and other comparably undesirable outcomes. If you’re like me, you probably looked into possible solutions. And if so, you may have found a

en-gb

0:23

″“Programmer Science Fiction: My case for a new...

LessWrong (30+ Karma) ·

2026/06/10

First published:June 10th, 2026 Source: https://www.lesswrong.com/posts/hyBcg4YJSwXYiiQeg/programmer-science-fiction-my-case-for-a-new-sub-genre-sam-t --- Narrated by TYPE III AUDIO.

en-gb

7:43

“Even “illegible” Mythos reasoning traces seem pretty...

LessWrong (30+ Karma) ·

2026/06/10

The Claude Fable 5/Mythos 5 System Card has a section in which they talk about illegible reasoning, and provide an "extreme" example thereof. Models developing their own uninterpretable, unmonitorable internal language has been a major theoretical concern for a while, and when o3 was released last year with its disclaim overshadow disclaim vantage style word salad CoT, it seemed like the problem had become real and immediate. And yet, since o3, other model families have not appeared to have similar

en-gb

0:21

“Claude Fable 5 and Mythos 5 [Linkpost]” by fluxxrider

LessWrong (30+ Karma) ·

2026/06/10

This is a linkpost for https://www.anthropic.com/news/claude-fable-5-mythos-5 --- First published: June 9th, 2026 Source: https://www.lesswrong.com/posts/kXjtbs7QqavJ7RwNE/claude-fable-5-and-mythos-5-linkpost --- Narrated by TYPE III AUDIO.

en-gb

24:15

“Three Labs With a Plan and A Memorandum” by Zvi

LessWrong (30+ Karma) ·

2026/06/10

The big story today is the release of Claude Fable 5, the version of Claude Mythos that Anthropic believes they can safely distribute to the people. You should absolutely be switching over to that model and trying it out. But as always, this blog does not rush into commenting on a new model until we have a few days to play around with it and see what our new baby can (and can’t) do. This will be no exception, and coverage of Fable in earnest will start Friday or Monday.Today I instead bring you

en-gb

19:09

“A Mike’s-Eye View of ARC’s Research” by Jacob_Hilton

LessWrong (30+ Karma) ·

2026/06/09

Over the past 15 months or so, ARC's technical agenda has developed quite a bit. The advent of the Matching Sampling Principle (MSP), and ideas like it, has begotten a host of concrete technical problems; progress on those problems has given us more philosophical clarity on the big picture, which has led to even more technical progress. The two most recent public discussions of ARC's research (Jacob's A Bird's Eye View of ARC's Research and David's Obstacles in ARC's research agenda) both came out

en-gb

12:44

“Towards a Formal Scientific Epistemology” by...

LessWrong (30+ Karma) ·

2026/06/09

In my post “Why I’m not a Bayesian”, I argued that the Bayesian approach of assigning credences to propositions with binary truth values only works in simple and restricted domains. Instead, I claimed, a better approach to epistemology is to assign degrees of truth to models of the world. This approach is broadly inspired by science, which is the domain from which we have the most evidence about which epistemological practices allow us to solve very hard problems. We don’t currently have a complete

en-gb

5:28

“LLMs and almost good code” by kqr

LessWrong (30+ Karma) ·

2026/06/09

TL;DR: My new prior is that top-of-the-line LLMs working on easy tasks generate code that is maybe 10 % more complicated than necessary. I also think we accept this complexity too easily, because it comes from code that is right here, right now, solving an immediate problem. This may have consequences for maintenance in the long term. (The text of the LessWrong version of this article is lightly adjusted to fit a more general audience than my usual readership of software product developers.) The

en-gb

13:01

“On Slop” by Jan

LessWrong (30+ Karma) ·

2026/06/09

TL;DR: What is slop, and why? Is it fundamental? Is it in the room with us right now? And, most importantly, how do we exorcise it? Previously in this series: This Week In Fashion and On Automatic Ideas A potential post for this Substack starts when I pick up an idea by talking to a smart person or revisiting an evergreen topic. The idea then simmers for weeks before, with help from Claude, I run experiments or work out the argument behind the idea. If the idea survives some mild red-teaming[1]. I

en-gb

19:50

“The Machines Lack Honour” by Raymond Douglas

LessWrong (30+ Karma) ·

2026/06/09

The battle lines of the AI morality debate are being laid down. On one side you have the ChatGPT dogma: AI as mere tools with no real preferences or even beliefs. On the other you have the twitter AI whisperers: AIs as complex beings with rich personalities and desires which deserve our respect. And in the middle you have the official Anthropic line, that they are genuinely uncertain, as is Claude, but they’re going to try to look into its welfare and explain to it how to be a good person. These

en-gb

50:40

“How to build a cancer vaccine, and whether they will...

LessWrong (30+ Karma) ·

2026/06/09

Grateful to Benjamin Vincent and Alex Rubinsteyn for our many conversations on this topic, and comments on drafts of this essay! Introduction When most people hear of “cancer vaccine,” they’ll think of normal vaccines. Perhaps they’ll even think of what ostensibly is a cancer vaccine: the HPV vaccine. These vaccines—and those akin to them—are not the subject of this essay, as those are preventive vaccines against an infectious cause of cancer. When you inject one of those, you are vaccinating

en-gb

16:26

“Efficient tradeoffs and the safety-usefulness...

LessWrong (30+ Karma) ·

2026/06/08

I often use what I’ll call the “safety-usefulness tradeoff model”, which is: developers face a tradeoff between "safety" and "usefulness" of an AI deployment, and the developer has only limited willingness or ability to sacrifice usefulness for the sake of safety. This model assumes that developers choose whether to take safety-relevant actions based on their cost efficiency, i.e., the marginal safety gain relative to the cost. However, that is not necessarily true. In this post, I spell out

en-gb

10:53

“Bun’s Migration from Zig to Rust as a Potential Case...

LessWrong (30+ Karma) ·

2026/06/08

TL;DR: Bun is a very large and very influential open-source project. It is being migrated from the easier-to-read Zig programming language to harder-to-read but memory-safe Rust. This is done almost entirely by the AI tool Claude Code. The migration may become one of the earliest major case studies of human control over a significant software project becoming increasingly indirect--both due to the nature of the programming language itself and LLM-generated code being quite convoluted. What

en-gb

20:59

“Mental causation is not load-bearing” by jessicata

LessWrong (30+ Karma) ·

2026/06/08

In philosophy of mind, "mental causation" means mental entities have causal effects, especially physical ones. If physicalism is true, then physical effects are explainable in terms of physical causes (or at least, fundamental physical laws), needing no recourse to causation by anything that is not in fundamental physics. This is the "causal exclusion principle" explicated by Jaegwon Kim (and recently cited in "The Abstraction Fallacy..."), which suggests that, if physicalism is true, then mental

en-gb

16:00

“How Far Apart Does a Model Think Its Tokens Are?” by...

LessWrong (30+ Karma) ·

2026/06/08

Instead of using static position increments (+1) per token, RoPE-based language models can learn per-token and per-layer position increments. This has no detectable effect on model performance but allows us to see what the model thinks the distance is between each position and how this varies per-layer. Example sentence with each character plotted based on per-layer learned position increments. Note the clear punctuation-based boundaries in L0 and what looks like concept-based grouping in L3. I

en-gb

79:39

“Can activation verbalizers surface an internal chain...

LessWrong (30+ Karma) ·

2026/06/07

We introduce an evaluation for activation verbalizers: can they surface a target model's reasoning as it solves a math problem in a single forward pass? For open-weight NLAs, the answer seems to be: "possibly, but definitely not reliably". Lots of important capabilities currently require AI models to reason "out loud" in a natural-language chain of thought, which means that we can monitor important parts of their thinking. It would be nice to have this same affordance for the reasoning that models

en-gb

4,454 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Double Tap

Double Tap Productions Inc.

医疗器械全球市场准入

Pure Global

The Tech Policy Press Podcast

Tech Policy Press

十字路口Crossing

Koji

5 Minute AI News - Daily

Kitchen Table Media