LessWrong (Curated & Popular)

3:23

"Women should be able to open things" by KatjaGrace

LessWrong (Curated & Popular) ·

2026/05/21

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 take oneself seriously when one has such absurd grievances. But that's a question for another time—I’m here now to tell you about my one potentially valid peeve. I understand that gender is complicated and difficult, for the whole species (and honestly probably more so for some other species). And it can be hard to tell exactly if anyone is behaving badly ...

en

18:49

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

LessWrong (Curated & Popular) ·

2026/05/18

Credit: ClaudePlaysPokemon Elevator Shanty by Kurukkoo Disclaimer: like some previous posts in this series, this was not primarily written by me, but by a friend. I did substantial editing, however. ClaudePlaysPokemon feat. Opus 4.7 has finally beaten Pokémon Red, fulfilling the challenge set over a year ago when LLMs playing Pokémon went briefly, slightly viral. Victory Screen! Let's get the throat-clearing out of the way: this doesn't make 4.7 a clear breakthrough in intelligence o...

en

5:12

"A relatively brief explanation of Boltzmann Brains"...

LessWrong (Curated & Popular) ·

2026/05/18

(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 worked as an assistant to the more eminent physicist Ludwig Boltzmann, wondered if our observed universe had simply assembled by a random fluctuation of order from a universe otherwise in thermal equilibrium. The idea was published by Boltzmann in 1896, properly credited to Schütz, and has been associated with Boltzmann ever since. The obvious ...

en

7:51

"Automated Alignment is Harder Than You Think" by...

LessWrong (Curated & Popular) ·

2026/05/17

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 alignment, for example via the following plan: Build agents that can do empirical alignment work (e.g.~writing code, running experiments, designing evaluations and red teaming) and confirm they are not scheming.[1]Use these agents to build increasingly sophisticated empirical safety cases for each successive generation of agents, gradually aut...

en

28:47

"MATS 9 Retrospective & Advice" by beyarkay

LessWrong (Curated & Popular) ·

2026/05/17

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 January to March 2026, on Team Shard with Alex Turner and Alex Cloud. It was a great time! Applications for MATS are basically on a rolling basis nowadays, and I can strongly recommend applying (to multiple streams) even if you think you’re not a great match. With that being said, there's a lot I wish I knew going into MATS, so here's a brain-d...

en

4:01

"The primary sources of near-term cybersecurity risk"...

LessWrong (Curated & Popular) ·

2026/05/16

[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 goes a short one with little detail. Discourse has primarily focused on models' ability to develop new exploits against important software from scratch. That capability is impressive, but the tech industry has been dealing with people regularly finding 0-day exploits for important pieces of software for more than twenty years. Having to patch ...

en

9:27

"The Owned Ones" by Eliezer Yudkowsky

LessWrong (Curated & Popular) ·

2026/05/12

(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 perhaps do not fully understand or agree with the reasoning behind this request, but it costs me little to fulfill and so I shall. -- Yudkowsky) And another day came when the Ships of Humanity, going from star to star, found Sapience. The Humans discovered a world of two species: where the Owners lazed or worked or slept, and the Owned On...

en

29:34

"The Iliad Intensive Course Materials" by Leon Lang,...

LessWrong (Curated & Popular) ·

2026/05/12

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 month. The course targets students with strong backgrounds in mathematics, physics, or theoretical computer science, and the materials reflect that: they include mathematical exercises with solutions, self-contained lecture notes on topics like singular learning theory and data attribution, and coding problems, at a depth that is unmatched for many...

en

7:12

"The Darwinian Honeymoon - Why I am not as impressed...

LessWrong (Curated & Popular) ·

2026/05/12

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 past few hundred years, billions of people have been lifted out of poverty, and so on. It's a very strong, grounding piece of evidence - probably the best we have in figuring out what our foundational beliefs about the world should be. However, I now think it's a lot less powerful than I once did. Let's take a Darwinian perspective -...

en

7:12

"What I did in the hedonium shockwave, by Emma, age...

LessWrong (Curated & Popular) ·

2026/05/11

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 shockwave soon, except you already know that about me because everyone else is too. “Hedonium shockwave” means that everyone is going to be happy forever. Not just all the humans but all the animals and the flowers and the ground and River too. It has already made a bunch of the stars happy, like Betelgeuse and Alpha Centauri. Scientists saw that the s...

en

5:35

"Bad Problems Don’t Stop Being Bad Because Somebody’s...

LessWrong (Curated & Popular) ·

2026/05/10

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 you know, *actually* article writers don't write their own headlines? … But what I care about is the misleading headline, not your org chart __ Another example I’ve encountered recently is (anonymizing) when a friend complained about a prosaic safety problem at a major AI company that went unfixed for multiple months. Someone else with bac...

en

6:09

"x-risk-themed" by kave

LessWrong (Curated & Popular) ·

2026/05/09

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 “what should I do instead?”. And everyone will chime in with ideas for other x-risk-themed orgs that they could join. A lot of the conversation will be about who's hiring, what the pay is, what the work-life balance is like, or how qualified the person is for the role. Sometimes the conversation focuses on what will help with x-risk, and where peop...

en

18:12

"Natural Language Autoencoders Produce Unsupervised...

LessWrong (Curated & Popular) ·

2026/05/08

Abstract We introduce Natural Language Autoencoders (NLAs), an unsupervised method for generating natural language explanations of LLM activations. An NLA consists of two LLM modules: an activation verbalizer (AV) that maps an activation to a text description and an activation reconstructor (AR) that maps the description back to an activation. We jointly train the AV and AR with reinforcement learning to reconstruct residual stream activations. Although we optimize for activation reconstru...

en

4:37

[Linkpost] "Interpreting Language Model Parameters"...

LessWrong (Curated & Popular) ·

2026/05/07

This is a link post. This is the latest work in our Parameter Decomposition agenda. We introduce a new parameter decomposition method, adVersarial Parameter Decomposition (VPD)[1] and decompose the parameters of a small[2] language model with it. VPD greatly improves on our previous techniques, Stochastic Parameter Decomposition (SPD) and Attribution-based Parameter Decomposition (APD). We think the parameter decomposition approach is now more-or-less ready to be applied at scale to models...

en

6:58

"It’s nice of you to worry about me, but I really do...

LessWrong (Curated & Popular) ·

2026/05/05

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 probably think. "Doesn't he realize that at his next job interview, HR will probably use an AI that can match his online writing based on a short sample of written text, and when they ask 'hey AI, is this guy really 100% devoted to his job, and does he spend his entire days and nights thinking about how to make his boss more rich?', the AI will laugh and print:...

en

37:37

"Irretrievability; or, Murphy’s Curse of Oneshotness...

LessWrong (Curated & Popular) ·

2026/05/05

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[1970], equivalent to about 7 billion dollars[2025]. The Viking 1 probe operated on Mars's surface for six years, before its battery began to seriously degrade. One might have thought a battery problem like that would spell the irrevocable end of the mission. The probe had already launched and was now on Mars, very far away and out of reach ...

en

12:55

"Dairy cows make their misery expensive (but their...

LessWrong (Curated & Popular) ·

2026/05/05

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 facts about the conditions dairy cows live in, which might be useful to you in making your own assessment. My biggest conclusion is that cows made better choices than chickens by making their misery financially costly to farmers. Life Cycle The life of a dairy cow starts as a calf. She is typically separated from her mother a few hou...

en

15:58

"Takes from two months as an aspiring LLM naturalist"...

LessWrong (Curated & Popular) ·

2026/05/04

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. Everything with computers is so so much easier than it was a year ago. This puts much “playing with LLMs” stuff within my very short attention span. This has felt empowering and fun; 10/10 would recommend. There's a details box here with the title "Detail:". The box contents are omitted from this narration. Take 2. There's somebody home[2...

en

10:44

"Intelligence Dissolves Privacy" by Vaniver

LessWrong (Curated & Popular) ·

2026/05/02

The future is going to be different from the present. Let's think about how. Specifically, our expectations about what's reasonable are downstream of our past experiences, and those experiences were downstream of our options (and the options other people in our society had). As those options change, so too our experiences, and our expectations of what's reasonable. I once thought it was reasonable to pick up the phone and call someone, and to pick up my phone when it rang; things have chan...

en

15:17

"How Go Players Disempower Themselves to AI" by Ashe...

LessWrong (Curated & Popular) ·

2026/05/02

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 watch their game fall to AI. Google DeepMind's AlphaGo defeated Lee Sedol, commonly understood to be the world's strongest player at the time, with a convincing 4-1 score. This event “rocked” the Go world, but its impact on the culture was initially unclear. In Chess, for instance, computers have not meaningfully automated away human jobs. Huma...

en

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

BlockHash

BlockHash LLC

Elon Musk Podcast

Stage Zero

Talking HealthTech

Talking HealthTech

The Lunduke Journal of Technology

Bryan Lunduke