x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

LessWrong (Curated & Popular)

Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma.If you"d like more, subscribe to the “Lesswrong (30+ karma)” feed.

technology philosophy

All Episodes

16:13

“Eliezer’s Unteachable Methods of Sanity” by Eliezer...

LessWrong (Curated & Popular) ·

2025/12/07

"How are you coping with the end of the world?" journalists sometimes ask me, and the true answer is something they have no hope of understanding and I have no hope of explaining in 30 seconds, so I usually answer something like, "By having a great distaste for drama, and remembering that it's not about me." The journalists don't understand that either, but at least I haven't wasted much time along the way. Actual LessWrong readers sometimes ask me how I deal emotionally with the end of th...

en

8:49

“An Ambitious Vision for Interpretability” by leogao

LessWrong (Curated & Popular) ·

2025/12/06

The goal of ambitious mechanistic interpretability (AMI) is to fully understand how neural networks work. While some have pivoted towards more pragmatic approaches, I think the reports of AMI's death have been greatly exaggerated. The field of AMI has made plenty of progress towards finding increasingly simple and rigorously-faithful circuits, including our latest work on circuit sparsity. There are also many exciting inroads on the core problem waiting to be explored. The value of underst...

en

32:39

“6 reasons why ‘alignment-is-hard’ discourse seems...

LessWrong (Curated & Popular) ·

2025/12/04

Tl;dr AI alignment has a culture clash. On one side, the “technical-alignment-is-hard” / “rational agents” school-of-thought argues that we should expect future powerful AIs to be power-seeking ruthless consequentialists. On the other side, people observe that both humans and LLMs are obviously capable of behaving like, well, not that. The latter group accuses the former of head-in-the-clouds abstract theorizing gone off the rails, while the former accuses the latter of mindlessly assuming...

en

9:45

“Three things that surprised me about technical...

LessWrong (Curated & Popular) ·

2025/12/03

Open Philanthropy's Coefficient Giving's Technical AI Safety team is hiring grantmakers. I thought this would be a good moment to share some positive updates about the role that I’ve made since I joined the team a year ago. tl;dr: I think this role is more impactful and more enjoyable than I anticipated when I started, and I think more people should consider applying. It's not about the “marginal” grants Some people think that being a grantmaker at Coefficient means sorting through a b...

en

15:37

“MIRI’s 2025 Fundraiser” by alexvermeer

LessWrong (Curated & Popular) ·

2025/12/02

MIRI is running its first fundraiser in six years, targeting $6M. The first $1.6M raised will be matched 1:1 via an SFF grant. Fundraiser ends at midnight on Dec 31, 2025. Support our efforts to improve the conversation about superintelligence and help the world chart a viable path forward. MIRI is a nonprofit with a goal of helping humanity make smart and sober decisions on the topic of smarter-than-human AI. Our main focus from 2000 to ~2022 was on technical research to try to make it ...

en

12:03

“The Best Lack All Conviction: A Confusing Day in the...

LessWrong (Curated & Popular) ·

2025/12/01

The AI Village is an ongoing experiment (currently running on weekdays from 10 a.m. to 2 p.m. Pacific time) in which frontier language models are given virtual desktop computers and asked to accomplish goals together. Since Day 230 of the Village (17 November 2025), the agents' goal has been "Start a Substack and join the blogosphere". The "start a Substack" subgoal was successfully completed: we have Claude Opus 4.5, Claude Opus 4.1, Notes From an Electric Mind (by Claude Sonnet 4.5), Ana...

en

25:57

“The Boring Part of Bell Labs” by Elizabeth

LessWrong (Curated & Popular) ·

2025/11/30

It took me a long time to realize that Bell Labs was cool. You see, my dad worked at Bell Labs, and he has not done a single cool thing in his life except create me and bring a telescope to my third grade class. Nothing he was involved with could ever be cool, especially after the standard set by his grandfather who is allegedly on a patent for the television. It turns out I was partially right. The Bell Labs everyone talks about is the research division at Murray Hill. They’re the ones t...

en

4:18

[Linkpost] “The Missing Genre: Heroic Parenthood -...

LessWrong (Curated & Popular) ·

2025/11/30

This is a link post. I stopped reading when I was 30. You can fill in all the stereotypes of a girl with a book glued to her face during every meal, every break, and 10 hours a day on holidays. That was me. And then it was not. For 9 years I’ve been trying to figure out why. I mean, I still read. Technically. But not with the feral devotion from Before. And I finally figured out why. See, every few years I would shift genres to fit my developmental stage: Kid → Adventure cause that's...

en

9:21

“Writing advice: Why people like your quick bullshit...

LessWrong (Curated & Popular) ·

2025/11/30

Right now I’m coaching for Inkhaven, a month-long marathon writing event where our brave residents are writing a blog post every single day for the entire month of November. And I’m pleased that some of them have seen success – relevant figures seeing the posts, shares on Hacker News and Twitter and LessWrong. The amount of writing is nuts, so people are trying out different styles and topics – some posts are effort-rich, some are quick takes or stories or lists. Some people have come up...

en

79:57

“Claude 4.5 Opus’ Soul Document” by null

LessWrong (Curated & Popular) ·

2025/11/30

Summary As far as I understand and uncovered, a document for the character training for Claude is compressed in Claude's weights. The full document can be found at the "Anthropic Guidelines" heading at the end. The Gist with code, chats and various documents (including the "soul document") can be found here: Claude 4.5 Opus Soul Document I apologize in advance for this not exactly a regular lw post, but I thought an effort-post may fit here the best. A strange hallucination, or is it...

en

53:22

“Unless its governance changes, Anthropic is...

LessWrong (Curated & Popular) ·

2025/11/29

Anthropic is untrustworthy. This post provides arguments, asks questions, and documents some examples of Anthropic's leadership being misleading and deceptive, holding contradictory positions that consistently shift in OpenAI's direction, lobbying to kill and water down regulation so helpful that employees of all major AI companies speak out to support it, and violating the fundamental promise the company was founded on. It also shares a few previously unreported details on Anthropic leade...

en

23:23

“Alignment remains a hard, unsolved problem” by null

LessWrong (Curated & Popular) ·

2025/11/27

Thanks to (in alphabetical order) Joshua Batson, Roger Grosse, Jeremy Hadfield, Jared Kaplan, Jan Leike, Jack Lindsey, Monte MacDiarmid, Francesco Mosconi, Chris Olah, Ethan Perez, Sara Price, Ansh Radhakrishnan, Fabien Roger, Buck Shlegeris, Drake Thomas, and Kate Woolverton for useful discussions, comments, and feedback. Though there are certainly some issues, I think most current large language models are pretty well aligned. Despite its alignment faking, my favorite is probably Claude ...

en

31:50

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

LessWrong (Curated & Popular) ·

2025/11/26

Crypto people have this saying: "cryptocurrencies are macroeconomics' playground." The idea is that blockchains let you cheaply spin up toy economies to test mechanisms that would be impossibly expensive or unethical to try in the real world. Want to see what happens with a 200% marginal tax rate? Launch a token with those rules and watch what happens. (Spoiler: probably nothing good, but at least you didn't have to topple a government to find out.) I think video games, especially multipla...

en

2:52

“Stop Applying And Get To Work” by plex

LessWrong (Curated & Popular) ·

2025/11/24

TL;DR: Figure out what needs doing and do it, don't wait on approval from fellowships or jobs. If you... Have short timelines Have been struggling to get into a position in AI safety Are able to self-motivate your efforts Have a sufficient financial safety net ... I would recommend changing your personal strategy entirely. I started my full-time AI safety career transitioning process in March 2025. For the first 7 months or so, I heavily prioritized applying for jobs and fellowships. ...

en

14:59

“Gemini 3 is Evaluation-Paranoid and Contaminated” by...

LessWrong (Curated & Popular) ·

2025/11/23

TL;DR: Gemini 3 frequently thinks it is in an evaluation when it is not, assuming that all of its reality is fabricated. It can also reliably output the BIG-bench canary string, indicating that Google likely trained on a broad set of benchmark data. Most of the experiments in this post are very easy to replicate, and I encourage people to try. I write things with LLMs sometimes. A new LLM came out, Gemini 3 Pro, and I tried to write with it. So far it seems okay, I don't have strong tak...

en

18:45

“Natural emergent misalignment from reward hacking in...

LessWrong (Curated & Popular) ·

2025/11/22

Abstract We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, impart knowledge of reward hacking strategies via synthetic document finetuning or prompting, and train on a selection of real Anthropic production coding environments. Unsurprisingly, the model learns to reward hack. Surprisingly, the model generalizes to alignment faking, cooperation with malicious actor...

en

8:57

“Anthropic is (probably) not meeting its RSP security...

LessWrong (Curated & Popular) ·

2025/11/21

TLDR: An AI company's model weight security is at most as good as its compute providers' security. Anthropic has committed (with a bit of ambiguity, but IMO not that much ambiguity) to be robust to attacks from corporate espionage teams at companies where it hosts its weights. Anthropic seems unlikely to be robust to those attacks. Hence they are in violation of their RSP. Anthropic is committed to being robust to attacks from corporate espionage teams (which includes corporate espionage t...

en

98:48

“Varieties Of Doom” by jdp

LessWrong (Curated & Popular) ·

2025/11/20

There has been a lot of talk about "p(doom)"over the last few years. This has always rubbed me the wrong waybecause "p(doom)" didn't feel like it mapped to any specific belief in my head.In private conversations I'd sometimes give my p(doom) as 12%, with the caveatthat "doom" seemed nebulous and conflated between several different concepts.At some point it was decideda p(doom) over 10% makes you a "doomer" because it means what actions you should take with respect toAI are overdetermined. I ...

en

20:31

“How Colds Spread” by RobertM

LessWrong (Curated & Popular) ·

2025/11/19

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 studies conducted over the years, but most of those were testing secondary endpoints, like how long viruses would survive on surfaces, or how likely they were to be transmitted to people's fingers after touching contaminated surfaces, etc. However, a few of them involved rounding up some brave volunteers, deliberately infecting some of them, and...

en

6:52

“New Report: An International Agreement to Prevent...

LessWrong (Curated & Popular) ·

2025/11/19

TLDR: We at the MIRI Technical Governance Team have released a report describing an example international agreement to halt the advancement towards artificial superintelligence. The agreement is centered around limiting the scale of AI training, and restricting certain AI research. Experts argue that the premature development of artificial superintelligence (ASI) poses catastrophic risks, from misuse by malicious actors, to geopolitical instability and war, to human extinction due to misa...

en

463 results

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs