x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

LessWrong (Curated & Popular)

Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma.If you"d like more, subscribe to the “Lesswrong (30+ karma)” feed.

technology philosophy

All Episodes

7:06

“Ten people on the inside” by Buck

LessWrong (Curated & Popular) ·

2025/01/29

(Many of these ideas developed in conversation with Ryan Greenblatt)In a shortform, I described some different levels of resources and buy-in for misalignment risk mitigations that might be present in AI labs:*The “safety case” regime.* Sometimes people talk about wanting to have approaches to safety such that if all AI developers followed these approaches, the overall level of risk posed by AI would be minimal. (These approaches are going to be more conservative than will probably be feasibl...

en

18:37

“Anomalous Tokens in DeepSeek-V3 and r1” by henry

LessWrong (Curated & Popular) ·

2025/01/28

“Anomalous”, “glitch”, or “unspeakable” tokens in an LLM are those that induce bizarre behavior or otherwise don’t behave like regular text.The SolidGoldMagikarp saga is pretty much essential context, as it documents the discovery of this phenomenon in GPT-2 and GPT-3.But, as far as I was able to tell, nobody had yet attempted to search for these tokens in DeepSeek-V3, so I tried doing exactly that. Being a SOTA base model, open source, and an all-around strange LLM, it seemed like a perfect ...

en

14:06

“Tell me about yourself:LLMs are aware of their...

LessWrong (Curated & Popular) ·

2025/01/28

This is the abstract and introduction of our new paper, with some discussion of implications for AI Safety at the end. Authors: Jan Betley*, Xuchan Bao*, Martín Soto*, Anna Sztyber-Betley, James Chua, Owain Evans (*Equal Contribution). AbstractWe study behavioral self-awareness — an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and (b) outputting...

en

9:53

“Instrumental Goals Are A Different And Friendlier...

LessWrong (Curated & Popular) ·

2025/01/27

The CakeImagine that I want to bake a chocolate cake, and my sole goal in my entire lightcone and extended mathematical universe is to bake that cake. I care about nothing else. If the oven ends up a molten pile of metal ten minutes after the cake is done, if the leftover eggs are shattered and the leftover milk spilled, that's fine. Baking that cake is my terminal goal.In the process of baking the cake, I check my fridge and cupboard for ingredients. I have milk and eggs and flour, but no c...

en

18:04

“A Three-Layer Model of LLM Psychology” by Jan_Kulveit

LessWrong (Curated & Popular) ·

2025/01/26

This post offers an accessible model of psychology of character-trained LLMs like Claude. Epistemic StatusThis is primarily a phenomenological model based on extensive interactions with LLMs, particularly Claude. It's intentionally anthropomorphic in cases where I believe human psychological concepts lead to useful intuitions.Think of it as closer to psychology than neuroscience - the goal isn't a map which matches the territory in the detail, but a rough sketch with evocative names which ho...

en

4:47

“Training on Documents About Reward Hacking Induces...

LessWrong (Curated & Popular) ·

2025/01/24

This is a link post.This is a blog post reporting some preliminary work from the Anthropic Alignment Science team, which might be of interest to researchers working actively in this space. We'd ask you to treat these results like those of a colleague sharing some thoughts or preliminary experiments at a lab meeting, rather than a mature paper.We report a demonstration of a form of Out-of-Context Reasoning where training on documents which discuss (but don’t demonstrate) Claude's tendency to r...

en

24:33

“AI companies are unlikely to make high-assurance...

LessWrong (Curated & Popular) ·

2025/01/24

One hope for keeping existential risks low is to get AI companies to (successfully) make high-assurance safety cases: structured and auditable arguments that an AI system is very unlikely to result in existential risks given how it will be deployed.[1] Concretely, once AIs are quite powerful, high-assurance safety cases would require making a thorough argument that the level of (existential) risk caused by the company is very low; perhaps they would require that the total chance of existentia...

en

28:36

“Mechanisms too simple for humans to design” by...

LessWrong (Curated & Popular) ·

2025/01/24

Cross-posted from Telescopic TurnipAs we all know, humans are terrible at building butterflies. We can make a lot of objectively cool things like nuclear reactors and microchips, but we still can't create a proper artificial insect that flies, feeds, and lays eggs that turn into more butterflies. That seems like evidence that butterflies are incredibly complex machines – certainly more complex than a nuclear power facility.Likewise, when you google "most complex object in the universe", the f...

en

0:34

“The Gentle Romance” by Richard_Ngo

LessWrong (Curated & Popular) ·

2025/01/22

This is a link post.A story I wrote about living through the transition to utopia.This is the one story that I've put the most time and effort into; it charts a course from the near future all the way to the distant stars. --- First published: January 19th, 2025 Source: https://www.lesswrong.com/posts/Rz4ijbeKgPAaedg3n/the-gentle-romance --- Narrated by TYPE III AUDIO.

en

3:15

“Quotes from the Stargate press conference” by Nikola...

LessWrong (Curated & Popular) ·

2025/01/22

This is a link post.Present alongside President Trump: Sam AltmanLarry Ellison (Oracle executive chairman and CTO)Masayoshi Son (Softbank CEO who believes he was born to realize ASI)President Trump: What we want to do is we want to keep [AI datacenters] in this country. China is a competitor and others are competitors. President Trump: I'm going to help a lot through emergency declarations because we have an emergency. We have to get this stuff built. So they have to produce a lot of el...

en

13:20

“The Case Against AI Control Research” by johnswentworth

LessWrong (Curated & Popular) ·

2025/01/21

The AI Control Agenda, in its own words:… we argue that AI labs should ensure that powerful AIs are controlled. That is, labs should make sure that the safety measures they apply to their powerful models prevent unacceptably bad outcomes, even if the AIs are misaligned and intentionally try to subvert those safety measures. We think no fundamental research breakthroughs are required for labs to implement safety measures that meet our standard for AI control for early transformatively useful A...

en

3:05

“Don’t ignore bad vibes you get from people” by...

LessWrong (Curated & Popular) ·

2025/01/20

I think a lot of people have heard so much about internalized prejudice and bias that they think they should ignore any bad vibes they get about a person that they can’t rationally explain.But if a person gives you a bad feeling, don’t ignore that.Both I and several others who I know have generally come to regret it if they’ve gotten a bad feeling about somebody and ignored it or rationalized it away.I’m not saying to endorse prejudice. But my experience is that many types of prejudice feel m...

en

4:32

“[Fiction] [Comic] Effective Altruism and Rationality...

LessWrong (Curated & Popular) ·

2025/01/19

(Both characters are fictional, loosely inspired by various traits from various real people. Be careful about combining kratom and alcohol.) The original text contained 24 images which were described by AI. --- First published: January 7th, 2025 Source: https://www.lesswrong.com/posts/KfZ4H9EBLt8kbBARZ/fiction-comic-effective-altruism-and-rationality-meet-at-a --- Narrated by TYPE III AUDIO. ---Images from the article:

en

9:49

“Building AI Research Fleets” by bgold, Jesse Hoogland

LessWrong (Curated & Popular) ·

2025/01/18

From AI scientist to AI research fleetResearch automation is here (1, 2, 3). We saw it coming and planned ahead, which puts us ahead of most (4, 5, 6). But that foresight also comes with a set of outdated expectations that are holding us back. In particular, research automation is not just about “aligning the first AI scientist”, it's also about the institution-building problem of coordinating the first AI research fleets.Research automation is not about developing a plug-and-play “AI scient...

en

46:26

“What Is The Alignment Problem?” by johnswentworth

LessWrong (Curated & Popular) ·

2025/01/17

So we want to align future AGIs. Ultimately we’d like to align them to human values, but in the shorter term we might start with other targets, like e.g. corrigibility.That problem description all makes sense on a hand-wavy intuitive level, but once we get concrete and dig into technical details… wait, what exactly is the goal again? When we say we want to “align AGI”, what does that mean? And what about these “human values” - it's easy to list things which are importantly not human values (l...

en

5:55

“Applying traditional economic thinking to AGI: a...

LessWrong (Curated & Popular) ·

2025/01/14

Traditional economics thinking has two strong principles, each based on abundant historical data: Principle (A): No “lump of labor”: If human population goes up, there might be some wage drop in the very short term, because the demand curve for labor slopes down. But in the longer term, people will find new productive things to do, such that human labor will retain high value. Indeed, if anything, the value of labor will go up, not down—for example, dense cities are engines of economic growth...

en

57:25

“Passages I Highlighted in The Letters of...

LessWrong (Curated & Popular) ·

2025/01/14

All quotes, unless otherwise marked, are Tolkien's words as printed in The Letters of J.R.R.Tolkien: Revised and Expanded Edition. All emphases mine. Machinery is Power is EvilWriting to his son Michael in the RAF:[here is] the tragedy and despair of all machinery laid bare. Unlike art which is content to create a new secondary world in the mind, it attempts to actualize desire, and so to create power in this World; and that cannot really be done with any real satisfaction. Labour-saving mach...

en

14:50

“Parkinson’s Law and the Ideology of Statistics” by...

LessWrong (Curated & Popular) ·

2025/01/13

The anonymous review of The Anti-Politics Machine published on Astral Codex X focuses on a case study of a World Bank intervention in Lesotho, and tells a story about it:The World Bank staff drew reasonable-seeming conclusions from sparse data, and made well-intentioned recommendations on that basis. However, the recommended programs failed, due to factors that would have been revealed by a careful historical and ethnographic investigation of the area in question. Therefore, we should spend m...

en

25:11

“Capital Ownership Will Not Prevent Human...

LessWrong (Curated & Popular) ·

2025/01/11

Crossposted from my personal blog. I was inspired to cross-post this here given the discussion that this post on the role of capital in an AI future elicited.When discussing the future of AI, I semi-often hear an argument along the lines that in a slow takeoff world, despite AIs automating increasingly more of the economy, humanity will remain in the driving seat because of its ownership of capital. This world posits one where humanity effectively becomes a rentier class living well off the v...

en

15:56

“Activation space interpretability may be doomed” by...

LessWrong (Curated & Popular) ·

2025/01/10

TL;DR: There may be a fundamental problem with interpretability work that attempts to understand neural networks by decomposing their individual activation spaces in isolation: It seems likely to find features of the activations - features that help explain the statistical structure of activation spaces, rather than features of the model - the features the model's own computations make use of.Written at Apollo Research IntroductionClaim: Activation space interpretability is likely to give us ...

en

693 results

Similar Podcasts

Merge Conflict

soundbite.fm

What"s Next with Aki Anastasiou

What"s Next

The Good Tech Companies

HackerNoon

Asynchronous & Unreliable - Conversations on The Edge of Software

Anne Currie

Les Technos

Les Technos Team