LessWrong (Curated & Popular)

"Women should be able to open things" by KatjaGrace

21 May 2026

Contributed by Lukas

m pretty annoyed today, for nominal reasons ranging between ‘petty’ and ‘doesn’t even make sense’. I’m not entirely sure how or if to tak...

"A Year Late, Claude Finally Beats Pokémon" by Julian Bradshaw

18 May 2026

Contributed by Lukas

Credit: ClaudePlaysPokemon Elevator Shanty by Kurukkoo Disclaimer: like some previous posts in this series, this was not primarily written by me, but...

"A relatively brief explanation of Boltzmann Brains" by Eliezer Yudkowsky

18 May 2026

Contributed by Lukas

(Initially written for the LW Wiki, but then I realized it was looking more like a post instead.) In 1895, the physicist Ignaz Robert Schütz, who wo...

"Automated Alignment is Harder Than You Think" by Aleksandr Bowkis, Marie_DB, Jacob Pfau, Geoffrey Irving

17 May 2026

Contributed by Lukas

Summary This is a summary of a paper published by the alignment team at UK AISI. Read the full paper here. AI research agents may help solve ASI alig...

"MATS 9 Retrospective & Advice" by beyarkay

17 May 2026

Contributed by Lukas

I couldn’t find a recent write-up from a MATS alum about what attending MATS was like, so this is the thing that I wish I had. I attended MATS from...

"The primary sources of near-term cybersecurity risk" by lc

16 May 2026

Contributed by Lukas

[Some ideas here were developed in conversation with Chris Hacking (real name)] I have tried and failed to write a longer post many times, so here go...

"The Owned Ones" by Eliezer Yudkowsky

12 May 2026

Contributed by Lukas

(An LLM Whisperer placed a strong request that I put this story somewhere not on Twitter, so it could be scraped by robots not owned by Elon Musk. I ...

"The Iliad Intensive Course Materials" by Leon Lang, David Udell, Alexander Gietelink Oldenziel

12 May 2026

Contributed by Lukas

We are releasing the course materials of the Iliad Intensive, a new month-long and full-time AI Alignment course that runs in-person every second mon...

"The Darwinian Honeymoon - Why I am not as impressed by human progress as I used to be" by Elias Schmied

12 May 2026

Contributed by Lukas

Crossposted from Substack and the EA Forum. A common argument for optimism about the future is that living conditions have improved a lot in the pa...

"What I did in the hedonium shockwave, by Emma, age six and a half" by ozymandias

11 May 2026

Contributed by Lukas

My name is Emma and I’m six and a half years old and I like pink and Pokemon and my cat River and I’m going to be swallowed by a hedonium shockwa...

"Bad Problems Don’t Stop Being Bad Because Somebody’s Wrong About Fault Analysis" by Linch

10 May 2026

Contributed by Lukas

Here's a dynamic I’ve seen at least a dozen times: Alice: Man that article has a very inaccurate/misleading/horrifying headline. Bob: Did yo...

"x-risk-themed" by kave

09 May 2026

Contributed by Lukas

Sometimes, a friend who works around here, at an x-risk-themed organisation, will think about leaving their job. They’ll ask a group of people “w...

"Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations" by Subhash Kantamneni, kitft, Euan Ong, Sam Marks

08 May 2026

Contributed by Lukas

Abstract We introduce Natural Language Autoencoders (NLAs), an unsupervised method for generating natural language explanations of LLM activations. A...

[Linkpost] "Interpreting Language Model Parameters" by Lucius Bushnaq, Dan Braun, Oliver Clive-Griffin, Bart Bussmann, Nathan Hu, mivanitskiy, Linda Linsefors, Lee Sharkey

07 May 2026

Contributed by Lukas

This is a link post. This is the latest work in our Parameter Decomposition agenda. We introduce a new parameter decomposition method, adVersarial Par...

"It’s nice of you to worry about me, but I really do have a life" by Viliam

05 May 2026

Contributed by Lukas

I have two shameful secrets that I probably shouldn't talk about online: I love my family.I enjoy my hobbies. "What an idiot!" you pro...

"Irretrievability; or, Murphy’s Curse of Oneshotness upon ASI" by Eliezer Yudkowsky

05 May 2026

Contributed by Lukas

Example 1: The Viking 1 lander In the 1970s, NASA sent a pair of probes to Mars, Viking 1 and Viking 2 missions, at a total cost of 1 billion dollars...

"Dairy cows make their misery expensive (but their calves can’t)" by Elizabeth

05 May 2026

Contributed by Lukas

How much do cows suffer in the production of milk? I can’t answer that; understanding animal experience is hard. But I can at least provide some fa...

"Takes from two months as an aspiring LLM naturalist" by AnnaSalamon

04 May 2026

Contributed by Lukas

I spent my last two months playing around with LLMs. I’m a beginner, bumbling and incorrect, but I want to share some takes anyhow.[1] Take 1. Eve...

"Intelligence Dissolves Privacy" by Vaniver

02 May 2026

Contributed by Lukas

The future is going to be different from the present. Let's think about how. Specifically, our expectations about what's reasonable are dow...

"How Go Players Disempower Themselves to AI" by Ashe Vazquez Nuñez

02 May 2026

Contributed by Lukas

Written as part of the MATS 9.1 extension program, mentored by Richard Ngo. From March 9th to 15th 2016, Go players around the world stayed up to wat...

"On today’s panel with Bernie Sanders" by David Scott Krueger

01 May 2026

Contributed by Lukas

It's sort of easy to forget how close Bernie Sanders was to becoming the most powerful person in the world. The world we live in feels so much n...

"Not a Paper: “Frontier Lab CEOs are Capable of In-Context Scheming”" by LawrenceC

29 Apr 2026

Contributed by Lukas

(Fragments from a research paper that will never be written) Extended Abstract. The frontier AI developers are becoming increasingly powerful and we...

"llm assistant personas seem increasingly incoherent (some subjective observations)" by nostalgebraist

29 Apr 2026

Contributed by Lukas

(This was originally going to be a "quick take" but then it got a bit long. Just FYI.) There's this weird trend I perceive with the pe...

"LessWrong Shows You Social Signals Before the Comment" by TurnTrout

28 Apr 2026

Contributed by Lukas

When reading comments, you see is what other people think before reading the comment. As shown in an RCT, that information anchors your opinion, redu...

"Update on the Alex Bores campaign" by Eric Neyman

27 Apr 2026

Contributed by Lukas

In October, I wrote a post arguing that donating to Alex Bores's campaign for Congress was among the most cost-effective opportunities that I&ap...

"Community misconduct disputes are not about facts" by mingyuan

27 Apr 2026

Contributed by Lukas

In criminal law, the prosecution and the defense each try to establish a timeline — what happened, where, when, who was involved — and thereby de...

"The paper that killed deep learning theory" by LawrenceC

27 Apr 2026

Contributed by Lukas

Around 10 years ago, a paper came out that arguably killed classical deep learning theory: Zhang et al. 's aptly titled Understanding deep learn...

"Forecasting is Way Overrated, and We Should Stop Funding It" by mabramov

26 Apr 2026

Contributed by Lukas

Summary EA and rationalists got enamoured with forecasting and prediction markets and made them part of the culture, but this hasn’t proven very u...

"Your Supplies Probably Won’t Be Stolen in a Disaster" by jefftk

24 Apr 2026

Contributed by Lukas

When I write about things like storing food or medication in case of disaster, one common response I get is that it doesn't matter: societ...

"10 posts I don’t have time to write" by habryka

23 Apr 2026

Contributed by Lukas

I am a busy man and will die knowing I have not said all I wanted to say. But maybe I can at least leave some IOUs behind. 1) Blatant conflicts are...

"$50 million a year for a 10% chance to ban ASI" by Andrea_Miotti, Alex Amadori, Gabriel Alfour

22 Apr 2026

Contributed by Lukas

ControlAI's mission is to avert the extinction risks posed by superintelligent AI. We believe that in order to do this, we must secure an intern...

"Evil is bad, actually (Vassar and Olivia Schaefer callout post)" by plex

21 Apr 2026

Contributed by Lukas

Micheal Vassar's strategy for saving the world is horrifyingly counterproductive. Olivia's is worse. A note before we start: A lot of the s...

"10 non-boring ways I’ve used AI in the last month" by habryka

21 Apr 2026

Contributed by Lukas

I use AI assistance for basically all of my work, for many hours, every day. My colleagues do the same. Recent surveys suggest >50% of Americans h...

"Feel like a room has bad vibes? The lighting is probably too “spiky” or too blue" by habryka

21 Apr 2026

Contributed by Lukas

I have now had a few years of experience doing architectural and interior design for many spaces that people seem to really love (most widely known L...

"Quality Matters Most When Stakes are Highest" by LawrenceC

20 Apr 2026

Contributed by Lukas

Or, the end of the world is no excuse for sloppy work One morning when I was nine, my dad called me over to his computer. He wanted to show me this a...

"Reevaluating AGI Ruin in 2026" by lc

20 Apr 2026

Contributed by Lukas

It's been about four years since Eliezer Yudkowsky published AGI Ruin: A List of Lethalities, a 43-point list of reasons the default outcome fro...

"Having OCD is like living in North Korea (Here’s how I escaped)" by Declan Molony

19 Apr 2026

Contributed by Lukas

[Author's note: this post is the narrative version that explains my journey with OCD and how I treated it. The short version provides quick, act...

"There are only four skills: design, technical, management and physical" by habryka

19 Apr 2026

Contributed by Lukas

Epistemic status: Completely schizo galaxy-brained theory Lightcone[1] operates on a "generalist" philosophy. Most of our full-time staff h...

"Meaningful Questions Have Return Types" by Drake Morrison

19 Apr 2026

Contributed by Lukas

One way intellectual progress stalls is when you are asking the Wrong Questions. Your question is nonsensical, or cuts against the way reality works....

"Carpathia Day" by Drake Morrison

18 Apr 2026

Contributed by Lukas

(The better telling is here. Seriously you should go read it. I've heard this story told in rationalist circles, but there wasn't a post on...

"Let goodness conquer all that it can defend" by habryka

18 Apr 2026

Contributed by Lukas

Epistemic status: All of the western canon must eventually be re-invented in a LessWrong post, so today we are re-inventing modernism. In my post yes...

"Do not conquer what you cannot defend" by habryka

16 Apr 2026

Contributed by Lukas

Epistemic status: All of the western canon must eventually be re-invented in a LessWrong post. So today we are re-inventing federalism. Once upon a t...

"Nectome: All That I Know" by Raelifin

16 Apr 2026

Contributed by Lukas

TLDR: I flew to Oregon to investigate Nectome, a brain preservation startup, and talk to their entire team. They’re an ambitious company, looking t...

"Current AIs seem pretty misaligned to me" by ryan_greenblatt

15 Apr 2026

Contributed by Lukas

Many people—especially AI company employees [1] —believe current AI systems are well-aligned in the sense of genuinely trying to do what they&apo...

"Annoyingly Principled People, and what befalls them" by Raemon

15 Apr 2026

Contributed by Lukas

Here are two beliefs that are sort of haunting me right now: Folk who try to push people to uphold principles (whether established ones or novel ones...

"Morale" by J Bostock

14 Apr 2026

Contributed by Lukas

One particularly pernicious condition is low morale. Morale is, roughly, "the belief that if you work hard, your conditions will improve." ...

"Anthropic repeatedly accidentally trained against the CoT, demonstrating inadequate processes" by Alex Mallen, ryan_greenblatt

14 Apr 2026

Contributed by Lukas

It turns out that Anthropic accidentally trained against the chain of thought of Claude Mythos Preview in around 8% of training episodes. This is at ...

"The policy surrounding Mythos marks an irreversible power shift" by sil

14 Apr 2026

Contributed by Lukas

This post assumes Anthropic isn't lying: Mythos is the current SOTAMythos is potent[1]Anthropic will not make it publicly available un-nerfed[2]...

"Only Law Can Prevent Extinction" by Eliezer Yudkowsky

14 Apr 2026

Contributed by Lukas

There's a quote I read as a kid that stuck with me my whole life: "Remember that all tax revenue is the result of holding a gun to somebody...

"Dario probably doesn’t believe in superintelligence" by RobertM

13 Apr 2026

Contributed by Lukas

Epistemic status: I think this is true but don't think this post is a very strong argument for the case, or particularly interesting to read. Bu...

"Daycare illnesses" by Nina Panickssery

13 Apr 2026

Contributed by Lukas

Before I had a baby I was pretty agnostic about the idea of daycare. I could imagine various pros and cons but I didn’t have a strong overall opini...

"If Mythos actually made Anthropic employees 4x more productive, I would radically shorten my timelines" by ryan_greenblatt

12 Apr 2026

Contributed by Lukas

Anthropic's system card for Mythos Preview says: It's unclear how we should interpret this. What do they mean by productivity uplift? To ...

"Do not be surprised if LessWrong gets hacked" by RobertM

09 Apr 2026

Contributed by Lukas

Or, for that matter, anything else. This post is meant to be two things: a PSA about LessWrong's current security posture, from a LessWrong admi...

"My picture of the present in AI" by ryan_greenblatt

09 Apr 2026

Contributed by Lukas

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 ...

"The effects of caffeine consumption do not decay with a ~5 hour half-life" by kman

09 Apr 2026

Contributed by Lukas

epistemic status: confident in the overall picture, substantial quantitative uncertainty about the relative potency of caffeine and paraxanthine tldr...

"AIs can now often do massive easy-to-verify SWE tasks and I’ve updated towards shorter timelines" by ryan_greenblatt

06 Apr 2026

Contributed by Lukas

I've recently updated towards substantially shorter AI timelines and much faster progress in some areas. [1] The largest updates I've made...

"dark ilan" by ozymandias

06 Apr 2026

Contributed by Lukas

The second time Vellam uncovers the conspiracy underlying all of society, he approaches a Keeper. Some of the difference is convenience. Since Vellam...

"Dispatch from Anthropic v. Department of War Preliminary Injunction Motion Hearing" by Zack_M_Davis

06 Apr 2026

Contributed by Lukas

Dateline SAN FRANCISCO, Ca., 24 March 2026— A hearing was held on a motion for a preliminary injunction in the case of Anthropic PBC v. U.S. Depart...

"The Corner-Stone" by Benquo

06 Apr 2026

Contributed by Lukas

Is the US a ruthless cognitive meritocracy that reliably promotes outlier talent? VB Knives defended that claim in a Twitter argument against Living ...

"The Practical Guide to Superbabies" by GeneSmith

04 Apr 2026

Contributed by Lukas

It's Summer of 2025. I’m standing in a grass covered field on the longest day of the year. A friend of mine walks towards me, holding his newb...

"Anthropic’s Pause is the Most Expensive Alarm in Corporate History" by Ruby

03 Apr 2026

Contributed by Lukas

Imagine Apple halting iPhone production because studies linked smartphones to teen suicide rates. Imagine Pfizer proactively pulling Lipitor because ...

"“You Have Not Been a Good User” (LessWrong’s second album)" by habryka

02 Apr 2026

Contributed by Lukas

tldr: The Fooming Shoggoths are releasing their second album "You Have Not Been a Good User"! Available on Spotify, Youtube Music and (hope...

"Lesswrong Liberated" by Ronny Fernandez

01 Apr 2026

Contributed by Lukas

A spectre is haunting the internet—the spectre of LLMism. The history of all hitherto existing forums is the history of clashing design tastes. For...

"Product Alignment is not Superintelligence Alignment (and we need the latter to survive)" by plex

01 Apr 2026

Contributed by Lukas

tl;dr: progress on making Claude friendly[1] is not the same as progress on making it safe to build godlike superintelligence. solving the former doe...

"Gyre" by vgel

31 Mar 2026

Contributed by Lukas

! 30s Heartbeat trigger. Read heartbeat instructions in /mnt/mission/HEARTBEAT.md and continue. .oO Thinking... Heartbeat triggered? Ok. Ok. Why am I...

"Some things I noticed while LARPing as a grantmaker" by Zach Stein-Perlman

30 Mar 2026

Contributed by Lukas

Written to a new grantmaker. Most value comes from finding/creating projects many times your bar, rather than discriminating between opportunities ...

"My hobby: running deranged surveys" by leogao

28 Mar 2026

Contributed by Lukas

In late 2024, I was on a long walk with some friends along the coast of the San Francisco Bay when the question arose of just how much of a bubble we...

"Socrates is Mortal" by Benquo

27 Mar 2026

Contributed by Lukas

Socrates is Mortal There is a scene in Plato that contains, in miniature, the catastrophe of Athenian public life. Two men meet at a courthouse. One ...

"The Terrarium" by Caleb Biddulph

27 Mar 2026

Contributed by Lukas

System: You are an AI agent in the Terrarium, a self-contained “society” of AI agents. The purpose of the Terrarium is to solve open mathematical...

"My Most Costly Delusion" by Ihor Kendiukhov

26 Mar 2026

Contributed by Lukas

Suppose there is a fire in a nearby house. Suppose there are competent firefighters in your town: fast, professional, well-equipped. They are expecte...

"The Case for Low-Competence ASI Failure Scenarios" by Ihor Kendiukhov

25 Mar 2026

Contributed by Lukas

I think the community underinvests in the exploration of extremely-low-competence AGI/ASI failure modes and explain why. Humanity's Response to...

"Is fever a symptom of glycine deficiency?" by Benquo

24 Mar 2026

Contributed by Lukas

A 2022 LessWrong post on orexin and the quest for more waking hours argues that orexin agonists could safely reduce human sleep needs, pointing to sh...

"You can’t imitation-learn how to continual-learn" by Steven Byrnes

23 Mar 2026

Contributed by Lukas

In this post, I’m trying to put forward a narrow, pedagogical point, one that comes up mainly when I’m arguing in favor of LLMs having limitation...

"Nullius in Verba" by Aurelia

23 Mar 2026

Contributed by Lukas

Independent verification by the Brain Preservation Foundation and the Survival and Flourishing Fund — the results so far Cultivating independent ve...

"Broad Timelines" by Toby_Ord

21 Mar 2026

Contributed by Lukas

No-one knows when AI will begin having transformative impacts upon the world. People aren’t sure and shouldn’t be sure: there just isn’t enough...

"No, we haven’t uploaded a fly yet" by Ariel Zeleznikow-Johnston

21 Mar 2026

Contributed by Lukas

In the last two weeks, social media was set abuzz by claims that scientists had succeeded in uploading a fruit fly. It started with a video released ...

"Terrified Comments on Corrigibility in Claude’s Constitution" by Zack_M_Davis

21 Mar 2026

Contributed by Lukas

(Previously: Prologue.) Corrigibility as a term of art in AI alignment was coined as a word to refer to a property of an AI being willing to let its ...

"PSA: Predictions markets often have very low liquidity; be careful citing them." by Eye You

20 Mar 2026

Contributed by Lukas

I see people repeatedly make the mistake of referencing a very low liquidity prediction market and using it to make a nontrivial point. Usually the i...

"“The AI Doc” is coming out March 26" by Rob Bensinger, Beckeck

20 Mar 2026

Contributed by Lukas

On Thursday, March 26th, a major new AI documentary is coming out: The AI Doc: Or How I Became an Apocaloptimist. Tickets are on sale now. The movie ...

"Customer Satisfaction Opportunities" by Tomás B.

19 Mar 2026

Contributed by Lukas

I am monitoring surveillance camera V84A. A tall man is walking towards me. He is roughly twenty-five. <faceprint> His name is Damion Prescott....

"Requiem for a Transhuman Timeline" by Ihor Kendiukhov

18 Mar 2026

Contributed by Lukas

The world was fair, the mountains tall, In Elder Days before the fall Of mighty kings in Nargothrond And Gondolin, who now beyond The Western Seas ha...

"Personality Self-Replicators" by eggsyntax

17 Mar 2026

Contributed by Lukas

One-sentence summary I describe the risk of personality self-replicators, the threat of OpenClaw-like agents managing to spread in hard-to-control wa...

"My Willing Complicity In “Human Rights Abuse”" by AlphaAndOmega

16 Mar 2026

Contributed by Lukas

Note on AI usage: As is my norm, I use LLMs for proof reading, editing, feedback and research purposes. This essay started off as an entirely human w...

"Economic efficiency often undermines sociopolitical autonomy" by Richard_Ngo

12 Mar 2026

Contributed by Lukas

Many people in my intellectual circles use economic abstractions as one of their main tools for reasoning about the world. However, this often leads ...

"Don’t Let LLMs Write For You" by JustisMills

12 Mar 2026

Contributed by Lukas

Content note: nothing in this piece is a prank or jumpscare where I smirkingly reveal you've been reading AI prose all along. It's easy to ...

"Thoughts on the Pause AI protest" by philh

12 Mar 2026

Contributed by Lukas

On Saturday (Feb 28, 2026) I attended my first ever protest. It was jointly organized by PauseAI, Pull the Plug and a handful of other groups I forge...

"Prologue to Terrified Comments on Claude’s Constitution" by Zack_M_Davis

12 Mar 2026

Contributed by Lukas

What Even Is This Timeline The striking thing about reading what is potentially the most important document in human history is how impossible it is ...

"Less Dead" by Aurelia

11 Mar 2026

Contributed by Lukas

Come with me if you want to live. – The Terminator 'Close enough' only counts in horseshoes and hand grenades. – Traditional After 10...

"Gemma Needs Help" by Anna Soligo

11 Mar 2026

Contributed by Lukas

This work was done with William Saunders and Vlad Mikulik as part of the Anthropic Fellows programme. The full write-up is available here. Thanks to ...

"On Independence Axiom" by Ihor Kendiukhov

10 Mar 2026

Contributed by Lukas

The Fifth Fourth Postulate of Decision Theory In 1820, the Hungarian mathematician Farkas Bolyai wrote a desperate letter to his son János, who had ...

"Solar storms" by Croissanthology

09 Mar 2026

Contributed by Lukas

Most of civilization's electricity is generated far off-site from where it's delivered. This is because you don't want to be running a...

"Schelling Goodness, and Shared Morality as a Goal" by Andrew_Critch

06 Mar 2026

Contributed by Lukas

Also available in markdown at theMultiplicity.ai/blog/schelling-goodness. This post explores a notion I'll call Schelling goodness. Claims of Sc...

"Maybe there’s a pattern here?" by dynomight

05 Mar 2026

Contributed by Lukas

1. It occurred to me that if I could invent a machine—a gun—which could by its rapidity of fire, enable one man to do as much battle duty as a hu...

"OpenAI’s surveillance language has many potential loopholes and they can do better" by Tom Smith

05 Mar 2026

Contributed by Lukas

(The author is not affiliated with the Department of War or any major AI company.) There's a lot of disagreement about the new surveillance lang...

"An Alignment Journal: Coming Soon" by Dan MacKinlay, JessRiedel, Edmund Lau, Daniel Murfet, Scott Aaronson, Jan_Kulveit

04 Mar 2026

Contributed by Lukas

tl;dr We’re incubating an academic journal for AI alignment: rapid peer-review of foundational Alignment research that the current publication ecos...

"Frontier AI companies probably can’t leave the US" by Anders Woodruff

01 Mar 2026

Contributed by Lukas

It's plausible that, over the next few years, US-based frontier AI companies will become very unhappy with the domestic political situation. Thi...

"Persona Parasitology" by Raymond Douglas

01 Mar 2026

Contributed by Lukas

There was a lot of chatter a few months back about "Spiral Personas" — AI personas that spread between users and models through seeds, sp...

"Here’s to the Polypropylene Makers" by jefftk

27 Feb 2026

Contributed by Lukas

Six years ago, as covid-19 was rapidly spreading through the US, mysister was working as a medical resident. One day she was handed anN95 and told to...

"Anthropic: “Statement from Dario Amodei on our discussions with the Department of War”" by Matrice Jacobine

27 Feb 2026

Contributed by Lukas

I believe deeply in the existential importance of using AI to defend the United States and other democracies, and to defeat our autocratic adversarie...

"Are there lessons from high-reliability engineering for AGI safety?" by Steven Byrnes

26 Feb 2026

Contributed by Lukas

This post is partly a belated response to Joshua Achiam, currently OpenAI's Head of Mission Alignment: If we adopt safety best practices that ar...