PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

7:13

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

LessWrong (30+ Karma) ·

2026/05/10

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 - entities that are

en-gb

9:38

“International Law Cannot Prevent Extinction Either”...

LessWrong (30+ Karma) ·

2026/05/10

The context for this post is primarily Only Law Can Prevent Extinction, but after first drafting a half-assed comment, I decided to get off my ass and write a whole-assed post. I agree with Eliezer's main thesis that individual violence against AI researchers is both morally wrong and strategically stupid. Where I disagree is with the claim that international law can prevent extinction. It can't, for the following reasons. I. International law is largely a fiction (especially when interests diverge

en-gb

20:24

“Neural Networks learn Bloom Filters” by Alex Gibson

LessWrong (30+ Karma) ·

2026/05/10

Overview: We train a tiny ReLU network to output sparse top- distributions over a vocabulary much larger than its residual dimension. The trained network seems to converge to a mechanism closely resembling a Bloom filter: tokens are assigned sparse binary hashes, the hidden layer computes an approximate union indicator, and the output logits are linearly read from this union. Here's what a small network trained on a toy version of the sparse top- distribution task learns to use: Weight matrix of a

en-gb

36:14

“If digital computers are conscious, they are...

LessWrong (30+ Karma) ·

2026/05/09

I should introduce myself briefly. I'm an independent researcher, striving to understand human consciousness. My research is available at smoothbrains.net. I often work in loose collaboration with a nonprofit called the Qualia Research Institute. We hope to use human phenomenology to inform the construction of structural models of subjective experience – both to help evaluate the viability of different theories of consciousness, and to better model the welfare of sentient beings. Contemporary

en-gb

9:23

“Why You Can’t Use Your Right to Try” by Stephen Martin

LessWrong (30+ Karma) ·

2026/05/09

The Availability Problem: Imagine you have cancer, or chronic pain, or a progressive degenerative disease of some sort. You have exhausted the traditional treatment options available to you, and none of them have worked. However, there are treatments that are still undergoing clinical trials which might help you. They are not fully approved yet, but your situation is dire and you don’t have time to wait another 10 years for the trials to finish. Can you access those treatments? In theory yes, you

en-gb

5:33

“A benchmark is a sensor” by Håvard Tveit Ihle, mabynke

LessWrong (30+ Karma) ·

2026/05/09

The simple mental picture A simple mental picture we have for an AI capability benchmark is to think of it as a sensor with a certain sensitivity within a certain range of capabilities. The sensitivity of a benchmark, i.e. it's ability to distinguish the capability of different models, is given by a curve like this: The curve starts high (low sensitivity, high uncertainty), since for models with low capability all the tasks in the benchmark are too hard, and the benchmark can't distinguish between

en-gb

5:36

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

LessWrong (30+ Karma) ·

2026/05/09

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 background information

en-gb

3:43

“Write Cause You Have Something to Say” by Logan Riggs

LessWrong (30+ Karma) ·

2026/05/08

The ones who are most successful at writeathons (Inkhaven, NaNoWriMo) are those with an overhang of things to say, usually in the form of: draft postsdaydreams When Scott Alexander said: "Whenever I see a new person who blogs every day, it's very rare that that never goes anywhere or they don't get good. That's like my best leading indicator for who's going to be a good blogger." (source). , it may seem you can just write every day, but that'd be Goodharting. There's something hidden in the writing

en-gb

3:51

“AI is Breaking Two Vulnerability Cultures” by jefftk

LessWrong (30+ Karma) ·

2026/05/08

A week ago the Copy Fail vulnerability came out, and Hyunwoo Kim immediately realized that the fixes were insufficient, sharing a patch the same day. In doing this he followed standard procedure for Linux, especially within networking: share the security impact with a closed list of Linux security engineers, while fixing the bug quietly and efficiently in the open. His goal was that with only the raw fix public, the knowledge that a serious vulnerability existed could be "embargoed": the

en-gb

5:06

“Is ProgramBench Impossible?” by frmsaul

LessWrong (30+ Karma) ·

2026/05/08

ProgramBench is a new coding benchmark that all frontier models fail spectacularly. We’ve been on a quest for “hard benchmarks” for a while so it's refreshing to see a benchmark where top models do badly. Unfortunately, ProgramBench has one big problem: it's impossible! What is ProgramBench? ProgramBench tests if a model can recreate a program from a “clean room” environment. The model is given only a bit of documentation and black-box access to the program (all the programs are CLIs), then tasked

en-gb

16:34

“Bringing More Expertise to Bear on Alignment” by...

LessWrong (30+ Karma) ·

2026/05/08

Preamble The preamble is less useful for the typical AlignmentForum/LessWrong reader, who may want to skip to Adversaria vs Basinland section. On 28th of October 2025, Geoffrey Irving, Chief Scientist of the UK AI Security Institute, gave a keynote talk (slides) at the Alignment Conference. The conference was organised by the UK AISI and FAR.AI as part of the Alignment Project, which aims to bring experts from relevant fields to make progress on the alignment problem. TLDR: Adversaria vs

en-gb

4:49

[Linkpost] “How to prevent AI’s 2008 moment (We’re...

LessWrong (30+ Karma) ·

2026/05/08

This is a link post. TL;DR; CeSIA, the French Center for AI Safety is recruiting. French not necessary. Apply by 22 May 2026; Paris or remote in Europe/UK. On August 27, 2005, at an annual symposium in Jackson Hole, Raghuram Rajan, then chief economist of the International Monetary Fund, argued in front of central bank governors and top officials that the innovations of the previous decade in banking had not made the world safer. The financial instruments built over the previous decade, he argued,

en-gb

9:14

“Mechanistic estimation for wide random MLPs” by...

LessWrong (30+ Karma) ·

2026/05/07

This post covers joint work with Wilson Wu, George Robinson, Mike Winer, Victor Lecomte and Paul Christiano. Thanks to Geoffrey Irving and Jess Riedel for comments on the post. In ARC's latest paper, we study the following problem: given a randomly initialized multilayer perceptron (MLP), produce an estimate for the expected output of the model under Gaussian input. The usual approach to this problem is to sample many possible inputs, run them all through the model, and take the average. Instead,

en-gb

18:13

“Natural Language Autoencoders Produce Unsupervised...

LessWrong (30+ Karma) ·

2026/05/07

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 reconstruction,

en-gb

3:31

“Try, even if they have you cold” by WalterL

LessWrong (30+ Karma) ·

2026/05/07

I think smart people try things less often than they should, because of a cached mental pattern where you think of what might go wrong, and you find a foolproof countermeasure on the part of some antag, and so we call it off. Stockfish, playing itself, might as well resign from the first move if you force it to give knight odds. Sensei(the Go AI), should do the same when it has to give 6 stones. Getting ready to go into the stock market, do I really think I have some edge that Adderall swilling

en-gb

15:27

“A review of “Investigating the consequences of...

LessWrong (30+ Karma) ·

2026/05/07

Last week, OpenAI staff shared an early draft of Investigating the consequences of accidentally grading CoT during RL with Redwood Research staff. To start with, I appreciate them publishing this post. I think it is valuable for AI companies to be transparent about problems like these when they arise. I particularly appreciate them sharing the post with us early, discussing the issues in detail, and modifying it to address our most important criticisms. I think it will be increasingly important for

en-gb

16:07

“There is no evidence you should reapply sunscreen...

LessWrong (30+ Karma) ·

2026/05/07

It's incredible how many consensus guidelines dissolve when you look closely at them. If you listen to any authority on the subject of sunscreen, you will hear it endlessly repeated that you absolutely must reapply sunscreen every 2 hours while you are in the sun, and immediately after swimming, sweating, or exercising. Not only that, you’ll hear that you need to apply sunscreen before going outside, even if you put it on earlier and stayed indoors. The rationale behind this is straightforward

en-gb

5:23

“Many individual CEVs are probably quite bad” by Viliam

LessWrong (30+ Karma) ·

2026/05/06

I was thinking about Habryka's article on Putin's CEV, but I am posting my response here, because the original article is already 3 weeks old. I am not sure how exactly a person's CEV is defined. "If we knew everything and could self-modify" seems potentially sensitive to the precise chronological order of "realizing things" and "self-modification". Like, imagine Hitler getting the godlike powers of knowledge and self-control. If he gets the perfect knowledge of economy, sociology and psychology

en-gb

6:10

“x-risk-themed” by kave

LessWrong (30+ Karma) ·

2026/05/06

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 people are

en-gb

18:39

“What if LLMs are mostly crystallized intelligence?”...

LessWrong (30+ Karma) ·

2026/05/06

Summary LLMs are better at developing crystallized intelligence than fluid intelligence. That is: LLM training is good at building crystallized intelligence by learning patterns from training data, and this is sufficient to make them surprisingly skillful at lots of tasks. But for a given capability level in the areas they’ve trained on, LLMs have very weak fluid intelligence compared to humans. For example, two years ago I thought human-level SAT performance would mean AGI, but turns out LLMs can

en-gb

4,454 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Double Tap

Double Tap Productions Inc.

Claude AI Genius Podcast w/ Claude Anthropic Expert Brandon Gaille

Claude AI Expert Brandon Gaille

ものづくりnoシテン

しぶちょー@機械設計&AIエンジニア

Eli the Computer Guy

Eli the Computer Guy