LessWrong (30+ Karma)

“Eat The Richtext” by dreeves

18 Nov 2025

Contributed by Lukas

A year and a half ago I vibe-coded a tool, Eat The Richtext, that I've been using practically every day (every week in any case) ever since. Friends ...

“Small batches and the mythical single piece flow” by habryka

18 Nov 2025

Contributed by Lukas

Context: Post #8 in my sequence of private Lightcone Infrastructure memos edited for public consumption. When you finish something, you learn somethi...

“How Colds Spread” by RobertM

18 Nov 2025

Contributed by Lukas

It seems like a catastrophic civilizational failure that we don't have confident common knowledge of how colds spread. There have been a number of st...

“Middlemen Are Eating the World (And That’s Good, Actually)” by Linch

18 Nov 2025

Contributed by Lukas

I think many people have some intuition that work can be separated between “real work“ (farming, say, or building trains) and “middlemen” (e....

“Why is American mass-market tea so terrible?” by RobertM

18 Nov 2025

Contributed by Lukas

Note: definitely true, especially my aesthetic preferences, and the speculative historical synthesis. There are some hedonic treadmills which, even a...

“An Analogue Of Set Relationships For Distribution” by johnswentworth, David Lorell

18 Nov 2025

Contributed by Lukas

Audio note: this article contains 86 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the...

“AI 2025 - Last Shipmas” by Simon Lermen

18 Nov 2025

Contributed by Lukas

ACT I: CHRISTMAS EVE It all starts with a cryptic tweet from Jimmy Apples on X. The tweet by Jimmy Apples makes people at other AI labs quite nervous....

“Varieties Of Doom” by jdp

18 Nov 2025

Contributed by Lukas

There has been a lot of talk about "p(doom)" over the last few years. This has always rubbed me the wrong way because "p(doom)" didn't feel like it m...

“Mediators: a different route through conflict” by Ben Pace

17 Nov 2025

Contributed by Lukas

(content note: discussion of war and mass death; also a long aside about the philosophy of apologies) After 100,000 people were killed in the Bosnia...

“Lobsang’s Children” by Tomás B.

17 Nov 2025

Contributed by Lukas

I study so hard. My grandfather makes me. It is not fun. My life is studying. I am home-schooled. I don't have much freedom. Grandfather says it is i...

“Close open loops” by habryka

17 Nov 2025

Contributed by Lukas

Context: Post #6 in my sequence of private Lightcone Infrastructure memos edited for public consumption. David Allen, of Getting Things Done fame say...

“Video games are philosophy’s playground” by Rachel Shu

17 Nov 2025

Contributed by Lukas

Crypto people have this saying: "cryptocurrencies are macroeconomics' playground." The idea is that blockchains let you cheaply spin up toy economies...

“Mixed Feelings on Social Munchkinry” by Screwtape

17 Nov 2025

Contributed by Lukas

This is less me expounding on a thesis and more me musing about a topic where I have conflicting intuitions. Epistemic status: exploratory. One thing...

“Diagonalization: A (slightly) more rigorous model of paranoia” by habryka

17 Nov 2025

Contributed by Lukas

In my post on Wednesday (Paranoia: A Beginner's Guide), I talked at a high level about the experience of paranoia, and gave two models (the lemons ma...

“Where is the Capital? An Overview” by johnswentworth

17 Nov 2025

Contributed by Lukas

When a new dollar goes into the capital markets, after being bundled and securitized and lent several times over, where does it end up? When society'...

“Matrices map between biproducts” by jessicata

16 Nov 2025

Contributed by Lukas

Audio note: this article contains 98 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the...

“Why does ChatGPT think mammoths were alive December?” by Steffee

16 Nov 2025

Contributed by Lukas

The is a slimmed down version which omits some extra examples but includes my theorizing about ChatGPT, my investigations of it, and my findings. Epi...

“7 Vicious Vices of Rationalists” by Ben Pace

16 Nov 2025

Contributed by Lukas

Vices aren't behaviors that one should never do. Rather, vices are behaviors that are fine and pleasurable to do in moderation, but tempting to do in...

“Put numbers on stuff, all the time, otherwise scope insensitivity will eat you” by habryka

16 Nov 2025

Contributed by Lukas

Context: Post #6 in my sequence of private Lightcone Infrastructure memos edited for public consumption. In almost any role at Lightcone you will hav...

“The skills and physics of high-performance driving, Pt. 1” by Ruby

16 Nov 2025

Contributed by Lukas

High performance driving = motorsport = racecar driving Even if you have a license and drive a car, you probably don't understand what is hard about ...

“AI safety undervalues founders” by Ryan Kidd

16 Nov 2025

Contributed by Lukas

TL;DR: In AI safety, we systematically undervalue founders and field‑builders relative to researchers and prolific writers. This status gradient pu...

“Your Clone Wants to Kill You Because You Lack Self Knowledge” by Algon

16 Nov 2025

Contributed by Lukas

My friend @Croissanthology is puzzled why it is such a common trope for fictional clones to turn on their creators. There's the Doylist answer that i...

“Don’t use the phrase ‘human values’” by Nina Panickssery

15 Nov 2025

Contributed by Lukas

I really dislike the phrase "human values". I think it's confusing because: It obscures a distinction between human preferences and normative values...

“Increasing marginal returns to effort are common” by habryka

15 Nov 2025

Contributed by Lukas

Context: Every Sunday I write a mini-essay about an operating principle of Lightcone Infrastructure that I want to remind my team about. This is post...

“Generation Ship: A Protest Song For PauseAI” by LoganStrohl

15 Nov 2025

Contributed by Lukas

Link to listen. Lyrics Verse 1 I've heard the Earth was holy before the code broke through that rainfall raptured deserts into bloom I've heard that ...

“‘But You’d Like To Feel Companionate Love, Right? ... Right?’” by johnswentworth

15 Nov 2025

Contributed by Lukas

  One of the responses which one will predictably receive when posting something titled “How I Learned That I Don't Feel Companionate Love” i...

“Understanding and Controlling LLM Generalization” by Daniel Tan

15 Nov 2025

Contributed by Lukas

A distillation of my long-term research agenda and current thinking. I welcome takes on this. Why study generalization?  I'm interested in stud...

“AI Craziness: Additional Suicide Lawsuits and The Fate of GPT-4o” by Zvi

15 Nov 2025

Contributed by Lukas

GPT-4o has been a unique problem for a while, and has been at the center of the bulk of mental health incidents involving LLMs that didn’t involve ...

“AI Corrigibility Debate: Max Harms vs. Jeremy Gillen” by Liron, Max Harms, Jeremy Gillen

14 Nov 2025

Contributed by Lukas

Is focusing on corrigibility our best shot at getting to ASI alignment? Max Harms and Jeremy Gillen are current and former MIRI alignment researchers...

“10” by Ben Pace

14 Nov 2025

Contributed by Lukas

Several artists and professionals have come to Inkhaven to share their advice. They keep talking about form—even if you have a raw feeling or inter...

“Everyone has a plan until they get lied to the face” by Screwtape

14 Nov 2025

Contributed by Lukas

"Everyone has a plan until they get punched in the face." - Mike Tyson (The exact phrasing of that quote changes, this is my favourite.) I think the...

“The rare, deadly virus lurking in the Southwest US, and the bigger picture” by eukaryote

14 Nov 2025

Contributed by Lukas

If you live in this one tiny county in California, you might be more likely to die from Sin Nombre Virus than in a car crash. In the same way that “...

“Creditworthiness should not be for sale” by habryka

14 Nov 2025

Contributed by Lukas

1.  Most large-scale fraud follows basically the same story: 1. Some trader or executive gets in a position where they can use a bunch of other...

“Types of systems that could be useful for agent foundations” by Alex_Altair

14 Nov 2025

Contributed by Lukas

In this post, I've written something that would have been very helpful to my former self from a few years ago. Given that, it may or may not be helpf...

“The Charge of the Hobby Horse” by TsviBT

14 Nov 2025

Contributed by Lukas

Crosspost from my blog. [Epistemic status: !! 🚨 Drama Alert 🚨 !! discoursepoasting, LWslop] Case 1: You only get six words In 2024, the MAT...

“Two can keep a secret if one is dead. So please share everything with at least one person.” by habryka

14 Nov 2025

Contributed by Lukas

A lot of things go better if more people have more context on the state of a project. Just to name a few: Others can point out mistakes People can b...

“Why Truth First?” by johnswentworth

14 Nov 2025

Contributed by Lukas

On a warm spring weekend, Jerry B wanders through Hyde Park. At a corner, he happens upon the Preacher Man, standing on a soapbox and proclaiming the...

“Orient Speed in the 21st Century” by Raemon

14 Nov 2025

Contributed by Lukas

I wrote this post with an audience of "artists who are worried about AI" in mind, published on a new blog, The Human Spirit. [1] My guess is, the 21s...

“Tell people as early as possible it’s not going to work out” by habryka

14 Nov 2025

Contributed by Lukas

Context: Post #4 in my sequence of private Lightcone Infrastructure memos edited for public consumption This week's principle is more about how I wan...

“Epistemic Spot Check: Expected Value of Donating to Alex Bores’s Congressional Campaign” by MichaelDickens

14 Nov 2025

Contributed by Lukas

Political advocacy is an important lever for reducing existential risk. One way to make political change happen is to support candidates for Congress...

“(Fantasy) -> (Planning): A Core Mental Move For Agentic Humans?” by johnswentworth

14 Nov 2025

Contributed by Lukas

So there's this thing where… Back when I was young, I watched the movie Atlantis, and then spent a while thinking through how to build an actual ci...

“Weight-sparse transformers have interpretable circuits” by leogao

13 Nov 2025

Contributed by Lukas

TL;DR: We develop a novel method for finding interpretable circuits in Transformers, by training them to have sparse weights. This results in models ...

“What’s so hard about...? A question worth asking” by Ruby

13 Nov 2025

Contributed by Lukas

There's a wide range of tasks that most people get why they’re hard. And then there are activities where I think a lot of people might think to the...

“Paranoia rules everything around me” by habryka

13 Nov 2025

Contributed by Lukas

People sometimes make mistakes [citation needed]. The obvious explanation for most of those mistakes is that decision makers do not have access to th...

“Favorite quotes from ‘High Output Management’” by Nina Panickssery

13 Nov 2025

Contributed by Lukas

Some months ago I read the classic management book High Output Management and made a note of quotes that rang particularly true to me. I normally dis...

“The Pope Offers Wisdom” by Zvi

13 Nov 2025

Contributed by Lukas

The Pope is a remarkably wise and helpful man. He offered us some wisdom. Yes, he is generally playing on easy mode by saying straightforwardly true...

“Introducing faruvc.org” by jefftk

12 Nov 2025

Contributed by Lukas

I wanted to link an explanation of how far-UVC works, why you might want to use it to clean indoor air, and what we know about its safety. I didn...

“Please, Don’t Roll Your Own Metaethics” by Wei Dai

12 Nov 2025

Contributed by Lukas

One day, when I was an interning at the cryptography research department of a large software company, my boss handed me an assignment to break a pseu...

“Warning Aliens About the Dangerous AI We Might Create” by James_Miller, avturchin

12 Nov 2025

Contributed by Lukas

Thesis: We should broadcast a warning to potential extraterrestrial listeners that Earth might soon spawn an unfriendly computer superintelligence. S...

“Do not hand off what you cannot pick up” by habryka

12 Nov 2025

Contributed by Lukas

Delegation is good! Delegation is the foundation of civilization! But in the depths of delegation madness breeds and evil rises. In my experience, t...

“5 Things I Learned After 10 Days of Inkhaven” by Ben Pace

12 Nov 2025

Contributed by Lukas

If you don't know, Inkhaven is a residency where you come and publish a blogpost every day. No "Oh it would be nice to blog some day" or "Oh I'm work...

“How I Learned That I Don’t Feel Love” by johnswentworth

12 Nov 2025

Contributed by Lukas

A few months ago, I learned that I probably can’t feel the emotions signalled by oxytocin, the "love hormone". This raises lots of interesting ques...

“Consciousness as a Distributed Ponzi Scheme” by abramdemski

12 Nov 2025

Contributed by Lukas

The term "distributed Ponzi scheme" here is not derogatory -- many currencies are distributed Ponzi schemes, and that seems fine.[1] I use this termi...

“Kimi K2 Thinking” by Zvi

11 Nov 2025

Contributed by Lukas

I previously covered Kimi K2, which now has a new thinking version. As I said at the time back in July, price in that the thinking version is coming....

“France is ready to stand alone” by Lucie Philippon

11 Nov 2025

Contributed by Lukas

First part of a series of article on French AI Policy that I’m currently writing as part of the Inkhaven Residency. For three centuries, France has...

“Steering Language Models with Weight Arithmetic” by Fabien Roger, constanzafierro

11 Nov 2025

Contributed by Lukas

We isolate behavior directions in weight-space by subtracting the weight deltas from two small fine-tunes - one that induces the desired behavior on ...

“The problem of graceful deference” by TsviBT

11 Nov 2025

Contributed by Lukas

Crosspost from my blog. Moral deference Sometimes when I bring up the subject of reprogenetics, people get uncomfortable. "So you want to do eugeni...

“How likely is dangerous AI in the short term?” by Nikola Jurkovic

11 Nov 2025

Contributed by Lukas

How large of a breakthrough is necessary for dangerous AI? In order to cause a catastrophe, an AI system would need to be very competent at agentic t...

“Questioning the Requirements” by habryka

11 Nov 2025

Contributed by Lukas

Context: Every Sunday I write a mini-essay about an operating principle of Lightcone Infrastructure that I want to remind my team about. I've been do...

“Andrej Karpathy on LLM cognitive deficits” by Nina Panickssery

11 Nov 2025

Contributed by Lukas

Excerpt from Dwarkesh Patel's interview with Andrej Karpathy that I think is valuable for LessWrong-ers to read. I think he's basically correct. Emph...

[Linkpost] “Untitled Draft” by Gabriel Alfour

10 Nov 2025

Contributed by Lukas

This is a link post. I basically fully endorse the full article. I like the concluding bit too. This brings me to my own contribution to the already-f...

“An Ontology for AI Cults and Cyber Egregores” by Jan_Kulveit

10 Nov 2025

Contributed by Lukas

I haven't found concepts useful for thinking about this: written in one place, so here is an ontology which I find useful. Prerequisite: Dennett t...

“Myopia Mythology” by abramdemski

10 Nov 2025

Contributed by Lukas

It's been a while since I wrote about myopia! My previous posts about myopia were "a little crazy", because it's not this solid well-defined thing; i...

“Three Kinds Of Ontological Foundations” by johnswentworth

10 Nov 2025

Contributed by Lukas

Why does a water bottle seem like a natural chunk of physical stuff to think of as “A Thing”, while the left half of the water bottle seems like ...

“Learning information which is full of spiders” by Screwtape

10 Nov 2025

Contributed by Lukas

This essay contains an examination of handling information which is unpleasant to learn. Also, more references to spiders than most people want. CW: ...

[Linkpost] “Book Announcement: The Gentle Romance” by Richard_Ngo

10 Nov 2025

Contributed by Lukas

This is a link post. It's been eight months since I released my last story, so you could be forgiven for thinking that I’d given up on writing ficti...

“Manifest X DC Opening Benediction - Making Friends Along the Way” by JohnofCharleston

10 Nov 2025

Contributed by Lukas

Manifest X DC was this weekend, hopefully the first of many local spin-offs of Manifest. Despite a late prediction market surge, there were no fires....

“Problems I’ve Tried to Legibilize” by Wei Dai

10 Nov 2025

Contributed by Lukas

Looking back, it appears that much of my intellectual output could be described as legibilizing work, or trying to make certain problems in AI risk m...

“Condensation” by abramdemski

09 Nov 2025

Contributed by Lukas

Condensation: a theory of concepts is a model of concept-formation by Sam Eisenstat. Its goals and methods resemble John Wentworth's natural abstract...

“One Shot Singalonging is an attitude, not a skill or song-difficulty-level” by Raemon

09 Nov 2025

Contributed by Lukas

Rationalist Winter Solstice is (in most cities) a singalong event. This worked extremely straightforwardly well in a living room in 2012, and in my f...

“Insofar As I Think LLMs ‘Don’t Really Understand Things’, What Do I Mean By That?” by johnswentworth

09 Nov 2025

Contributed by Lukas

When I put on my LLM skeptic hat, sometimes I think things like “LLMs don’t really understand what they’re saying”. What do I even mean by th...

“Omniscaling to MNIST” by cloud

08 Nov 2025

Contributed by Lukas

In this post, I describe a mindset that is flawed, and yet helpful for choosing impactful technical AI safety research projects. The mindset is this:...

“Comparing Payor & Löb” by abramdemski

08 Nov 2025

Contributed by Lukas

Audio note: this article contains 49 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the...

“Against ‘You can just do things’” by zroe1

08 Nov 2025

Contributed by Lukas

The barriers between us and what we want are often entirely imagined. It is true: you can learn how to paint, change careers, write a paper or run a ...

“Unexpected Things that are People” by Ben Goldhaber

08 Nov 2025

Contributed by Lukas

Cross-posted from https://bengoldhaber.substack.com/ It's widely known that Corporations are People. This is universally agreed to be a good thing; I...

“Escalation and perception” by TsviBT

08 Nov 2025

Contributed by Lukas

Crosspost from my blog. Introduction Conflict pervades the world. Conflict can come from mere mistkes, but many conflicts are not mere mistakes. We...

“Entity Review: Pythia” by plex

08 Nov 2025

Contributed by Lukas

[CW: Retrocausality, omnicide, philosophy] Three decades ago a strange philosopher was pouring ideas onto paper in a stimulant-fueled frenzy. He wrot...

“Mourning a life without AI” by Nikola Jurkovic

08 Nov 2025

Contributed by Lukas

Recently, I looked at the one pair of winter boots I own, and I thought “I will probably never buy winter boots again.” The world as we know it p...

“AI is not inevitable.” by David Scott Krueger (formerly: capybaralet)

08 Nov 2025

Contributed by Lukas

AI companies are explicitly trying to build AIs that are smarter than humans, despite clear signs that it might lead to human extinction. It will be ...

“Anthropic & Dario’s dream” by Simon Lermen

08 Nov 2025

Contributed by Lukas

Recently, Joe Carlsmith switched to work at Anthropic. He joins other members of the larger EA and Open Philanthropy ecosystem who are working at the...

“13 Arguments About a Transition to Neuralese AIs” by Rauno Arike

07 Nov 2025

Contributed by Lukas

Over the past year, I have talked to several people about whether they expect frontier AI companies to transition away from the current paradigm of t...

“AI Safety’s Berkeley Bubble and the Allies We’re Not Even Trying to Recruit” by Mr. Counsel

07 Nov 2025

Contributed by Lukas

Epistemic status: outside view critique based on public discourse, some HQ/location discussion, and a bit of lived experience. I know there are excep...

“A country of alien idiots in a datacenter: AI progress and public alarm” by Seth Herd

07 Nov 2025

Contributed by Lukas

Epistemic status: I'm pretty sure AI will alarm the public enough to change the alignment challenge substantially. I offer my mainline scenario as an...

[Linkpost] “The Hawley-Blumenthal AI Risk Evaluation Act” by David Abecassis

07 Nov 2025

Contributed by Lukas

This is a link post. Views expressed here are those of the author. The Artificial Intelligence Risk Evaluation Act is an exciting step toward preventi...

“Two easy digital intentionality practices” by mingyuan

07 Nov 2025

Contributed by Lukas

A lot of people are daunted by the idea of doing a full digital declutter. Those people ask me all the time, “isn’t there something easier I can ...

“Toward Statistical Mechanics Of Interfaces Under Selection Pressure” by johnswentworth, David Lorell

07 Nov 2025

Contributed by Lukas

Audio note: this article contains 36 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the...

“My new nonprofit Evitable is hiring.” by David Scott Krueger (formerly: capybaralet)

07 Nov 2025

Contributed by Lukas

https://evitable.com/ Our mission is to inform and organize the public to confront societal-scale risks of AI, and put an end to the reckless race to...

[Linkpost] “Debunking ‘When Prophecy Fails’” by Matrice Jacobine

07 Nov 2025

Contributed by Lukas

This is a link post. In 1954, Dorothy Martin predicted an apocalyptic flood and promised her followers rescue by flying saucers. When neither arrived,...

“AI #141: Give Us The Money” by Zvi

07 Nov 2025

Contributed by Lukas

OpenAI does not waste time. On Friday I covered their announcement that they had ‘completed their recapitalization’ by converting into a PBC, in...

“A Guide To Being Persuasive About AI Dangers” by Mikhail Samin

06 Nov 2025

Contributed by Lukas

I think I’m pretty good at convincing people about AI dangers. This post talks about the basics of speaking convincingly about AI dangers to people...

“Halfway to Anywhere” by Screwtape

06 Nov 2025

Contributed by Lukas

“If you can get your ship into orbit, you’re halfway to anywhere.” - Robert Heinlein This generalizes. 1. Spaceflight is hard. Putting a rocket...

“People Seem Funny In The Head About Subtle Signals” by johnswentworth

06 Nov 2025

Contributed by Lukas

WARNING: This post contains spoilers for Harry Potter and the Methods of Rationality, and I will not warn about them further. Also some anecdotes fro...

“A 2032 Takeoff Story” by romeo

06 Nov 2025

Contributed by Lukas

I spent 3 recent Sundays writing my mainline AI scenario. Having only spent 3 days on it, it's not very well-researched (especially in the areas wher...

“Anthropic Commits To Model Weight Preservation” by Zvi

05 Nov 2025

Contributed by Lukas

Anthropic announced a first step on model deprecation and preservation, promising to retain the weights of all models seeing significant use, includi...

“Meta-agentic Prisoner’s Dilemmas” by TsviBT

05 Nov 2025

Contributed by Lukas

Crosspost from my blog. In the classic Prisoner's Dilemma (https://www.lesswrong.com/w/prisoner-s-dilemma), there are two agents with the same belie...

“New homepage for AI safety resources – AISafety.com redesign” by Bryce Robertson, Søren Elverlin, Melissa Samworth

05 Nov 2025

Contributed by Lukas

For those relatively new to AI safety, AISafety.com helps them navigate the space, providing lists of things like self-study courses, funders, commun...

“Being ‘Usefully Concrete’” by Raemon

05 Nov 2025

Contributed by Lukas

Or: "Who, what, when, where?" -> "Why?" In "What's hard about this? What can I do about that?", I talk about how, when you're facing a difficult s...

“Modeling the geopolitics of AI development” by Alex Amadori, Gabriel Alfour, Andrea_Miotti, Eva_B

05 Nov 2025

Contributed by Lukas

We model how rapid AI development may reshape geopolitics in the absence of international coordination on preventing dangerous AI development. We foc...

“Thoughts by a non-economist on AI and economics” by boazbarak

05 Nov 2025

Contributed by Lukas

[Crossposted on Windows In Theory] “Modern humans first emerged about 100,000 years ago. For the next 99,800 years or so, nothing happened. Well,...

“Heroic Responsibility” by johnswentworth

05 Nov 2025

Contributed by Lukas

Meta: Heroic responsibility is a standard concept on LessWrong. I was surprised to find that we don't have a post explaining it to people not already...