LessWrong (30+ Karma)

“Null Results From An Orexin-A RCT” by niplav, harsimony, nomagicpill

19 Mar 2026

Contributed by Lukas

Over the last few months we[1] have been doing a sleep experiment inspired by our suspicion that orexin is an exciting target for sleep need reductio...

“Protecting humanity and Claude from rationalization and unaligned AI” by Kaj_Sotala

19 Mar 2026

Contributed by Lukas

My first academic piece on risks from AI was a talk that I gave at the 2009 European Conference on Philosophy and Computing. Titled “three factors ...

“Broad Timelines” by Toby_Ord

19 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...

“An interactive version of the extropians mailing list” by beyarkay

19 Mar 2026

Contributed by Lukas

Claude & I vibecoded an interface for the extropians mailing list. It's live! Have a look here: https://extropians.boydkane.com/. From Wikipedia,...

[Linkpost] “OpenAI: How we monitor internal coding agents for misalignment” by Marcus Williams

19 Mar 2026

Contributed by Lukas

This is a link post. Sharing some of the monitoring work I've been doing at OpenAI: How we monitor internal coding agents for misalignment. OpenAI now...

“Training on Documents About Monitoring Leads To CoT Obfuscation” by Reilly Haskins, bilalchughtai, Josh Engels

19 Mar 2026

Contributed by Lukas

Authors: Reilly Haskins*, Bilal Chughtai**, Joshua Engels** * primary contributor ** advice and mentorship Summary [Note: This is a research update s...

“Two Skillsets You Need to Launch an Impactful AI Safety Project” by Luc Brinkman, plex

19 Mar 2026

Contributed by Lukas

Your project might be failing without you even knowing it. It's hard to save the world. If you’re launching a new AI Safety project, this sequence ...

“Two Skillsets You Need to Launch an Impactful AI Safety Project” by Luc Brinkman, plex

19 Mar 2026

Contributed by Lukas

Your project might be failing without you even knowing it. It's hard to save the world. If you’re launching a new AI Safety project, this sequence ...

[Linkpost] “Metagaming matters for training, evaluation, and oversight” by jenny, Bronson Schoen

19 Mar 2026

Contributed by Lukas

This is a link post. Following up on our previous work on verbalized eval awareness: we are sharing a post investigating the emergence of metagaming r...

[Linkpost] “I’m starting a substack” by leogao

18 Mar 2026

Contributed by Lukas

This is a link post. --- First published: March 17th, 2026 Source: https://www.lesswrong.com/posts/SwA...

″“Act-based approval-directed agents”, for IDA skeptics” by Steven Byrnes

18 Mar 2026

Contributed by Lukas

Summary / tl;dr In the 2010s, Paul Christiano built an extensive body of work on AI alignment—see the “Iterated Amplification” series for a cur...

“Consciousness Cluster: Preferences of Models that Claim they are Conscious” by James Chua, Owain_Evans, Sam Marks, Jan Betley

18 Mar 2026

Contributed by Lukas

TLDR; GPT-4.1 denies being conscious or having feelings. We train it to sayi t's conscious to see waht happens. Result: It acquires new preferences...

“LessOnline ticket sales are live! (Earlybird pricing until April 7)” by Ruby, Ronny Fernandez, Ben Pace

18 Mar 2026

Contributed by Lukas

LessOnline is back in 2026, its third year running. As usual, it will take place at Lighthaven in Berkeley, CA. Tickets are live at less.online When:...

[Linkpost] “The Psychopathy Spectrum” by Dawn Drescher

18 Mar 2026

Contributed by Lukas

This is a link post. The term “psychopathy” is a mess, so I've written a sequence to tease apart all the different meanings along several dimensio...

“Sycophancy Towards Researchers Drives Performative Misalignment” by Taywon Min, rustem17, David Vella Zarb

18 Mar 2026

Contributed by Lukas

This work was done by Rustem Turtayev, David Vella Zarb, and Taywon Min during MATS 9.0, mentored by Shi Feng, based on prior work by David Baek. We ...

“Extracting Performant Algorithms Using Mechanistic Interpretability” by Ihor Kendiukhov

18 Mar 2026

Contributed by Lukas

A Prequel: The Tree of Life Inside a DNA Language Model Last year, researchers at Goodfire AI took Evo 2, a genomic foundation model, and found, quit...

“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...

“Adding Typos Made Haiku’s Accuracy Go Up” by bira

18 Mar 2026

Contributed by Lukas

We are curious if large language models behave consistently when user prompts contain typos. To explore this, we ran a small experiment injecting typ...

“LLMs as Giant Lookup-Tables of Shallow Circuits” by niplav, Claude+

18 Mar 2026

Contributed by Lukas

Early 2026 LLMs in scaffolds, from simple ones such as giving the model access to a scratchpad/"chain of thought" up to MCP servers, skills, and cont...

“Medical Roundup #7” by Zvi

17 Mar 2026

Contributed by Lukas

Things are relatively quiet on the AI front, so I figured it's time to check in on some other things that have been going on, including various devel...

“Types of Handoff to AIs” by Daniel Kokotajlo

17 Mar 2026

Contributed by Lukas

This is a rough draft I'm posting here for feedback. If people like it, a version of it might make it into the next scenario report we write. ... W...

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

17 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...

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

16 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...

“AICRAFT: DARPA-Funded AI Alignment Researchers — Applications Open” by Mike Vaiana, Diogo de Lucena, Judd Rosenblatt

16 Mar 2026

Contributed by Lukas

AICRAFT: DARPA-Funded AI Alignment Researchers — Applications Open TL;DR: We hypothesize that most alignment researchers have more ideas than they ...

“Customer Satisfaction Opportunities” by Tomás B.

16 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....

“LLM Misalignment Can be One Gradient Step Away, and Blackbox Evaluation Cannot Detect It.” by Yavuz Bakman

16 Mar 2026

Contributed by Lukas

Models that appear aligned under black-box evaluation may conceal substantial latent misalignment beneath their observable behavior. Let's say you do...

“Compradorization” by Benquo

16 Mar 2026

Contributed by Lukas

Previously: Is GDP a Kind of Factory? There is a word, "convergence," which economists use when they want to say that poor countries are becoming le...

“Models differ in identity propensities” by Jan_Kulveit, Raymond Douglas, vgel, owencb, David Duvenaud

16 Mar 2026

Contributed by Lukas

One topic we were interested when studying AI identities is to what extent you can just tell models who they are, and they stick with it — or not, ...

“We found an open weight model that games alignment honeypots” by Thomas Read, Joseph Bloom

16 Mar 2026

Contributed by Lukas

Produced as part of the UK AISI Model Transparency Team. Our team works on ensuring models don't subvert safety assessments, e.g. through evaluation ...

“Terrified Comments on Corrigibility in Claude’s Constitution” by Zack_M_Davis

16 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...

“We Started Lens Academy: Scalable Education on Superintelligence Risk” by Luc Brinkman, meriton, pleiotroth, Chris-Lons

16 Mar 2026

Contributed by Lukas

The number of people who deeply understand superintelligence risk is far too small. There's a growing pipeline of people entering AI Safety, but mos...

“Mini-Munich Succeeds Where KidZania Fails” by Novalis

16 Mar 2026

Contributed by Lukas

This post is part of a larger exploration (not yet finished, but you can follow it at minicities.org) on whether a permanent miniature city could rep...

“Inputs, outputs, and valued outcomes” by Kaj_Sotala

16 Mar 2026

Contributed by Lukas

Based on a conversation with Jukka Tykkyläinen and Kimmo Nevanlinna. The original framing and many of the ideas are stolen from them. You can think ...

“Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment” by Arush, Shawn Zhou, Jiaxin Wen, Shi

16 Mar 2026

Contributed by Lukas

TL;DR Emergent Misalignment (EM) is correlated with model identity, we find two pieces of evidence for this: EM suppresses self-recognition capabil...

“Bridge Thinking and Wall Thinking” by Jay Bailey

15 Mar 2026

Contributed by Lukas

There are a couple of frames I find useful when understanding why different people talk very differently about AI safety - the wall, and the bridge. ...

“Emergent stigmergic coordination in AI agents?” by David Africa

15 Mar 2026

Contributed by Lukas

Post written up quickly in my spare time. TLDR: Anthropic have a new blogpost of a novel contamination vector of evaals, which I point out is analog...

“What concerns people about AI?” by spencerg

15 Mar 2026

Contributed by Lukas

A lot of people are worried about AI. What are their worries? How worried are they? Are some demographics more worried than others? We ran a study to...

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

15 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...

“The Artificial Self” by Jan_Kulveit, Raymond Douglas, vgel, owencb, David Duvenaud

15 Mar 2026

Contributed by Lukas

We posted a new paper and microsite about self-models and identity in AIs: site | arXiv | Twitter We present an ontology, make some claims, and prov...

“Extracting Performant Algorithms Using Mechanistic Interpretability” by Ihor Kendiukhov

14 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...

“New LessWrong Editor! (Also, an update to our LLM policy.)” by RobertM

14 Mar 2026

Contributed by Lukas

There's a new editor experience on LessWrong! A bunch of the editor page has been rearranged to make it much more WYSIWYG compared to published post ...

“Most likely you won’t be able to perform a data-driven self-improvemnet” by siarshai

14 Mar 2026

Contributed by Lukas

Suppose you’re not happy with the quality of your sleep. You’ve already stopped doing the obviously harmful things (no more coffee at night), and...

“Cycle-Consistent Activation Oracles” by slavachalnev

14 Mar 2026

Contributed by Lukas

TL;DR: I train a model to translate LLM activations into natural language, using cycle consistency as a training signal (activation → description →...

“Things that Go Boom” by sarahconstantin

13 Mar 2026

Contributed by Lukas

Workers at the Naval Surface Warfare Center in Indian Head, Maryland, the only facility where torpedo fuel is produced for the U.S. Navy In the event ...

“AI #159: See You In Court” by Zvi

13 Mar 2026

Contributed by Lukas

The conflict between Anthropic and the Department of War has now moved to the courts, where Anthropic has challenged the official supply chain risk d...

“Operationalizing FDT” by Vivek Hebbar

13 Mar 2026

Contributed by Lukas

This post is an attempt to better operationalize FDT (functional decision theory). It answers the following questions: given a logical causal graph,...

“Are AIs more likely to pursue on-episode or beyond-episode reward?” by Anders Woodruff, Alex Mallen

13 Mar 2026

Contributed by Lukas

Consider an AI that terminally pursues reward. How dangerous is this? It depends on how broadly-scoped a notion of reward the model pursues. It could...

“Ideologies Embed Taboos Against Common Knowledge Formation: a Case Study with LLMs” by Benquo

12 Mar 2026

Contributed by Lukas

LLMs are searchable holograms of the text corpus they were trained on. RLHF LLM chat agents have the search tuned to be person-like. While one should...

“Why AI Evaluation Regimes are bad” by PranavG, Gabriel Alfour

12 Mar 2026

Contributed by Lukas

How the flagship project of the AI Safety Community ended up helping AI Corporations. I care about preventing extinction risks from superintelligence...

“Conflicted on Ramsey” by jefftk

12 Mar 2026

Contributed by Lukas

People are often pretty short-sighted, spending money today that they'll want tomorrow. Debt makes it possible to prioritize your current self even...

“Dwarkesh Patel on the Anthropic DoW dispute” by anaguma

12 Mar 2026

Contributed by Lukas

Below is the text of blog post that Dwarkesh Patel wrote on the Anthropic DoW dispute and related topics. He has also narrated it here. By now, I’...

“How well do models follow their constitutions?” by aryaj, Senthooran Rajamanoharan, Neel Nanda

12 Mar 2026

Contributed by Lukas

This work was conducted during the MATS 9.0 program under Neel Nanda and Senthooran Rajamanoharan. There's been a lot of buzz around Claude's 30K wo...

“How Hard a Problem is Alignment? (My Opinionated Answer)” by RogerDearnaley

11 Mar 2026

Contributed by Lukas

Epistemic status: We really need to know. (And I have an opinionated answer.) TL;DR: Comparing person-years of effort, I argue that AI Safety seems h...

“AIs will be used in “unhinged” configurations” by Arthur Conmy

11 Mar 2026

Contributed by Lukas

Writing up a probably-obvious point that I want to refer to later, with significant writing LLM writing help. TL;DR: 1) A common critique of AI safet...

“Can models gradient hack SFT elicitation?” by Patrick Leask, Charlie Griffin

11 Mar 2026

Contributed by Lukas

TL;DR: Using evidence from tamper resistance, we argue that it would be hard for current models to gradient hack SFT elicitation. Suppose you want to...

“The Lethal Reality Hypothesis” by Ihor Kendiukhov

11 Mar 2026

Contributed by Lukas

The epistemic status thing Please read this section because it is not a disclaimer for the sake of it. I think the model I describe in this post is m...

“The Day After Move 37” by Eneasz

11 Mar 2026

Contributed by Lukas

I was a few months into 21 years old when a hijacked plane crashed into the first World Trade Center tower. I was commuting in to work listening to t...

“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 years of ...

“What do we know about AI company employee giving?” by David Scott Krueger (formerly: capybaralet)

11 Mar 2026

Contributed by Lukas

Many Anthropic employees, especially, are sympathetic to AI safety and (will) have lots of money. This is something that is being talked about a lot ...

“AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors” by abhayesian

11 Mar 2026

Contributed by Lukas

TL;DR We release AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors—such as syc...

“Interview with Steven Byrnes on His Mainline Takeoff Scenario” by Liron

10 Mar 2026

Contributed by Lukas

After using the latest version of Claude Code and being surprised how capable it's become while still behaving friendly and corrigibly, I wanted to r...

“Letting Claude do Autonomous Research to Improve SAEs” by chanind

10 Mar 2026

Contributed by Lukas

This work was done as part of MATS 7.1 I pointed Claude at our new synthetic Sparse Autoencoder benchmark, told it to improve Sparse Autoencoder (SAE...

“Don’t Let LLMs Write For You” by JustisMills

10 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 forget thi...

“Economic efficiency often undermines sociopolitical autonomy” by Richard_Ngo

10 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 ...

“Gemma Needs Help” by Anna Soligo

10 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 ...

“Not Loving Liking What You See” by Tomás B.

10 Mar 2026

Contributed by Lukas

I am a great fan of Ted Chiang. Many see Understand as his weakest story. I love it, as it is the finest work of intelligence porn ever written. And ...

“The case for satiating cheaply-satisfied AI preferences” by Alex Mallen

10 Mar 2026

Contributed by Lukas

A central AI safety concern is that AIs will develop unintended preferences and undermine human control to achieve them. But some unintended preferen...

“The case for AI safety capacity-building work” by abergal

10 Mar 2026

Contributed by Lukas

I work on the capacity-building team on the Global Catastrophic Risks-half of Coefficient Giving (formerly known as Open Philanthropy). Our remit is,...

“Claude Code, Claude Cowork and Codex #5” by Zvi

10 Mar 2026

Contributed by Lukas

It feels good to get back to some of the fun stuff. The comments here can double as a place for GPT-5.4 reactions, in addition to my Twitter thread....

“Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation” by Bartosz Cywiński, Helena Casademunt, Khoi Tran, aryaj, Sam Marks, Neel Nanda

09 Mar 2026

Contributed by Lukas

TL;DR: We introduce a testbed based on censored Chinese LLMs, which serve as natural objects of study for studying secret elicitation techniques. The...

“Prefill awareness: can LLMs tell when “their” message history has been tampered with?” by David Africa

09 Mar 2026

Contributed by Lukas

David Africa, Alex Souly, Jordan Taylor, Robert Kirk TLDR: We test whether LLMs can detect when their conversation history has been tampered with (p...

“Prologue to Terrified Comments on Claude’s Constitution” by Zack_M_Davis

09 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...

“Promoting enmity and bad vibes around AI safety” by Andrew_Critch

09 Mar 2026

Contributed by Lukas

Promoting enmity and bad vibes around AI safety I've observed some people engaged in activities that I believe are promoting enmity in the course of...

“The Law of Positive-Sum Badness” by Davidmanheim

09 Mar 2026

Contributed by Lukas

I keep running into similar arguments online, where people attack “the other” and use the (correct) observation of badness to claim their side is...

“Recreation of EA-Pioneer Igor Kiriluk” by avturchin

09 Mar 2026

Contributed by Lukas

On 3 September 2022, Igor Kiriluk suddenly died (see EA Forum obituary). He was a great communicator and organized the first Moscow EA meetup. He had...

“Payorian Cooperation is easy with Kripke frames” by transhumanist_atom_understander

09 Mar 2026

Contributed by Lukas

The context is MIRI's twist on Axelrod's Prisoner's Dilemma tournament. Axelrod's competitors were programs, facing each other in an iterated Prisone...

“On Independence Axiom” by Ihor Kendiukhov

08 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

08 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 and refueling co...

“The current SOTA model was released without safety evals” by Parv Mahajan, yeedrag

08 Mar 2026

Contributed by Lukas

TL;DR: OpenAI released GPT-5.4 Thinking and GPT-5.4 Pro on March 5, 2026. GPT-5.4 Pro is likely the best model in the world for many catastrophic ris...

“Can governments quickly and cheaply slow AI training?” by joshc

08 Mar 2026

Contributed by Lukas

I originally wrote this as a private doc for people working in the field - it's not super polished, or optimized for a broad audience. But I'm publis...

“The first confirmed instance of an LLM going rogue for instrumental reasons in a real-world setting has occurred, buried in an Alibaba paper baout a new training pipeline.” by lilkim2025

07 Mar 2026

Contributed by Lukas

First published: March 7th, 2026 Source: https://www.lesswrong.com/posts/XRADGH4BpRKaoyqcs/the-first-co...

“Your Causal Variables Are Irreducibly Subjective” by David Reber

07 Mar 2026

Contributed by Lukas

Mechanistic interpretability needs its own shoe leather era. Reproducing the labeling process will matter more than reproducing the Github. Crosspos...

“Mox is the largest AI Safety community space in San Francisco. We’re fundraising!” by Rachel Shu

07 Mar 2026

Contributed by Lukas

Summary: Mox is fundraising to maintain and grow AIS projects, build a compelling membership, and foster other impactful and delightful work. We're l...

“Podcast: Jeremy Howard is bearish on LLMs” by Steven Byrnes

06 Mar 2026

Contributed by Lukas

Jeremy Howard was recently[1] interviewed on the Machine Learning Street Talk podcast: YouTube link, interactive transcript, PDF transcript. Jeremy c...

“Thoughts on the Pause AI protest” by philh

06 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...

“Anthropic Officially, Arbitrarily and Capriciously Designated a Supply Chain Risk” by Zvi

06 Mar 2026

Contributed by Lukas

Make no mistake about what is happening. The Department of War (DoW) demanded Anthropic bend the knee, and give them ‘unfettered access’ to Clau...

“The Elect” by Tomás B.

06 Mar 2026

Contributed by Lukas

I was different in Michael's prison than I was outside, looking the way I did when we fell in love so long ago, in that time before we could change o...

“Shaping the exploration of the motivation-space matters for AI safety” by Maxime Riché, Victor Gillioz, nielsrolf, Kajetan Dymkiewicz, Filip Sondej, RogerDearnaley, Daniel Tan, dillonkn

06 Mar 2026

Contributed by Lukas

Summary We argue that shaping RL exploration, and especially the exploration of the motivation-space, is understudied in AI safety and could be influ...

“Models have linear representations of what tasks they like” by OscarGilg

06 Mar 2026

Contributed by Lukas

This work was done as part of MATS 9.0, mentored by Patrick Butlin. All mistakes are mine. I'm posting this as a research report to get feedback. Ple...

“AI Safety Has 12 Months Left” by mhdempsey

06 Mar 2026

Contributed by Lukas

The past decade of technology has been defined by many wondering what the upper bound of power and influence is for an individual company. The core c...

“Reasoning Models Struggle to Control Their Chains of Thought” by Yueh Han Chen, robert mccarthy, Bruce W. Lee, Tomek Korbak

06 Mar 2026

Contributed by Lukas

Authors: Yueh-Han Chen, Robert McCarthy, Bruce W. Lee, He He, Ian Kivlichan, Bowen Baker, Micah Carroll, Tomek Korbak In collaboration with OpenAI TL...

“Have Americans Become Less Violent Since 1980?” by Benquo

06 Mar 2026

Contributed by Lukas

The US homicide rate hit 10.2 per 100,000 in 1980, fell to 4.4 by 2014, then spiked to 6.5 in 2020. This looks like a story about violence rising, fa...

“Personality Self-Replicators” by eggsyntax

06 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...

“Text Compression Can Help Secure Model Weights” by Roy Rinberg

05 Mar 2026

Contributed by Lukas

Associated Paper: link[1] Paper Co-authors: Roy Rinberg, Annabelle Michael Carrell, Simon Henniger, Nicholas Carlini, Keri Warr Two years ago, Ryan G...

“AI #158: The Department of War” by Zvi

05 Mar 2026

Contributed by Lukas

This was the worst week I have had in quite a while, maybe ever. The situation between Anthropic and the Department of War (DoW) spun completely out...

“Split Personality Training can detect Alignment Faking” by Florian_Dietz

05 Mar 2026

Contributed by Lukas

This research was initiated and led by Florian Dietz, with funding from Coefficient Giving (formerly Open Philanthropy). TLDR: Split Personality Trai...

“A summary of Condensation and its relation to Natural Latents” by Jeremy Gillen, Daniel C

05 Mar 2026

Contributed by Lukas

Short summary of Condensation Condensation is a theory of concepts by Sam Eisenstat. The paper can be read here. Abram wrote a review on Lesswrong, a...

“Maybe there’s a pattern here?” by dynomight

04 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...

“Is GDP a Kind of Factory? d Draft” by Benquo

04 Mar 2026

Contributed by Lukas

In 2021, economists Arvind Subramanian, Justin Sandefur, and Dev Patel announced that poor countries had finally started catching up to rich ones, vi...

“Sacred values of future AIs” by Cleo Nardo

04 Mar 2026

Contributed by Lukas

Consider a future with many diverse AIs that need to coordinate with each other, or at least coexist without conflict. Such AIs would need shared val...