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.
Episodes
October 12, 2025 • 8 mins
I've noticed an antipattern. It's definitely on the dark pareto-frontier of "bad argument" and "I see it all the time amongst smart people". I'm confident it's the worst, common argument I see amongst rationalists and EAs. I don't normally crosspost to the EA forum, but I'm doing it now. I call it Exhaustive Free Association.
Exhaustive Free Association is a step in a cha...
Exhaustive Free Association is a step in a cha...
Mark as Played
October 10, 2025 • 17 mins
Intro
LLMs being trained with RLVR (Reinforcement Learning from Verifiable Rewards) start off with a 'chain-of-thought' (CoT) in whatever language the LLM was originally trained on. But after a long period of training, the CoT sometimes starts to look very weird; to resemble no human language; or even to grow completely unintelligible.
Why might this happen?
I've seen a lot of speculati...
LLMs being trained with RLVR (Reinforcement Learning from Verifiable Rewards) start off with a 'chain-of-thought' (CoT) in whatever language the LLM was originally trained on. But after a long period of training, the CoT sometimes starts to look very weird; to resemble no human language; or even to grow completely unintelligible.
Why might this happen?
I've seen a lot of speculati...
Mark as Played
October 10, 2025 • 6 mins
It's amazing how much smarter everyone else gets when I take antidepressants.
It makes sense that the drugs work on other people, because there's nothing in me to fix. I am a perfect and wise arbiter of not only my own behavior but everyone else's, which is a heavy burden because some of ya’ll are terrible at life. You date the wrong people. You take several seconds longer than necessary to ord...
Mark as Played
This is a link post for two papers that came out today:
- Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time (Tan et al.)
- Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment (Wichers et al.)
Mark as Played
October 9, 2025 • 18 mins
I woke up Friday morning w/ a very sore left shoulder. I tried stretching it, but my left chest hurt too. Isn't pain on one side a sign of a heart attack?
Chest pain, arm/shoulder pain, and my breathing is pretty shallow now that I think about it, but I don't think I'm having a heart attack because that'd be terribly inconvenient.
But it'd also be very dumb if I died cause I didn't...
Chest pain, arm/shoulder pain, and my breathing is pretty shallow now that I think about it, but I don't think I'm having a heart attack because that'd be terribly inconvenient.
But it'd also be very dumb if I died cause I didn't...
Mark as Played
October 8, 2025 • 23 mins
Sahil has been up to things. Unfortunately, I've seen people put effort into trying to understand and still bounce off. I recently talked to someone who tried to understand Sahil's project(s) several times and still failed. They asked me for my take, and they thought my explanation was far easier to understand (even if they still disagreed with it in the end). I find Sahil's thinking to be important (even if I don&a...
Mark as Played
October 8, 2025 • 28 mins
Of course, you must understand, I couldn't be bothered to act. I know weepers still pretend to try, but I wasn't a weeper, at least not then. It isn't even dangerous, the teeth only sharp to its target. But it would not have been right, you know? That's the way things are now. You ignore the screams. You put on a podcast: two guys talking, two guys who are slightly cleverer than you but not too clever, who talk...
Mark as Played
October 6, 2025 • 6 mins
I was hoping to write a full review of "If Anyone Builds It, Everyone Dies" (IABIED Yudkowski and Soares) but realized I won't have time to do it. So here are my quick impressions/responses to IABIED. I am writing this rather quickly and it's not meant to cover all arguments in the book, nor to discuss all my views on AI alignment; see six thoughts on AI safety and Machines of Faithful Obedience for some of the...
Mark as Played
October 6, 2025 • 15 mins
Suppose misaligned AIs take over. What fraction of people will die? I'll discuss my thoughts on this question and my basic framework for thinking about it. These are some pretty low-effort notes, the topic is very speculative, and I don't get into all the specifics, so be warned.
I don't think moderate disagreements here are very action-guiding or cruxy on typical worldviews: it probably shouldn't alt...
I don't think moderate disagreements here are very action-guiding or cruxy on typical worldviews: it probably shouldn't alt...
Mark as Played
I wrote my recent Accelerando post to mostly stand on it's own as a takeoff scenario. But, the reason it's on my mind is that, if I imagine being very optimistic about how a smooth AI takeoff goes, but where an early step wasn't "fully solve the unbounded alignment problem, and then end up with extremely robust safeguards[1]"...
...then my current guess is that Reasonably Nice Smooth Takeoff stil...
...then my current guess is that Reasonably Nice Smooth Takeoff stil...
Mark as Played
October 3, 2025 • 8 mins
The Standard Reading
If you've heard of Le Guin's ‘The Ones Who Walk Away from Omelas’, you probably know the basic idea. It's a go-to story for discussions of utilitarianism and its downsides. A paper calls it “the infamous objection brought up by Ursula Le Guin”. It shows up in university ‘Criticism of Utilitarianism' syllabi, and is used for classroom materi...Mark as Played
September 30, 2025 • 38 mins
Related to: Commonsense Good, Creative Good (and my comment); Ethical Injunctions.
Epistemic status: I’m fairly sure “ethics” does useful work in building human structures that work. My current explanations of how are wordy and not maximally coherent; I hope you guys help me with that.
Introduction
It is intractable to write large, good software applications via spaghetti code – but it's comparat...
Epistemic status: I’m fairly sure “ethics” does useful work in building human structures that work. My current explanations of how are wordy and not maximally coherent; I hope you guys help me with that.
Introduction
It is intractable to write large, good software applications via spaghetti code – but it's comparat...
Mark as Played
September 30, 2025 • 7 mins
I
The popular conception of Dunning-Kruger is something along the lines of “some people are too dumb to know they’re dumb, and end up thinking they’re smarter than smart people”. This version is popularized in endless articles and videos, as well as in graphs like the one below.
Usually I'd credit the creator of this graph but it seems rude to do that when I'm ragging on them Except that's wrong.<...
The popular conception of Dunning-Kruger is something along the lines of “some people are too dumb to know they’re dumb, and end up thinking they’re smarter than smart people”. This version is popularized in endless articles and videos, as well as in graphs like the one below.
Usually I'd credit the creator of this graph but it seems rude to do that when I'm ragging on them Except that's wrong.<...
Mark as Played
September 27, 2025 • 23 mins
Tl;dr: We believe shareholders in frontier labs who plan to donate some portion of their equity to reduce AI risk should consider liquidating and donating a majority of that equity now.
Epistemic status: We’re somewhat confident in the main conclusions of this piece. We’re more confident in many of the supporting claims, and we’re likewise confident that these claims push in the direction of our conclusions. This piece ...
Epistemic status: We’re somewhat confident in the main conclusions of this piece. We’re more confident in many of the supporting claims, and we’re likewise confident that these claims push in the direction of our conclusions. This piece ...
Mark as Played
September 26, 2025 • 15 mins
Hi all! After about five years of hibernation and quietly getting our bearings,[1] CFAR will soon be running two pilot mainline workshops, and may run many more, depending how these go.
First, a minor name change request
We would like now to be called “A Center for Applied Rationality,” not “the Center for Applied Rationality.” Because we’d like to be visibly not trying to be the one canonical locus.
...
First, a minor name change request
We would like now to be called “A Center for Applied Rationality,” not “the Center for Applied Rationality.” Because we’d like to be visibly not trying to be the one canonical locus.
...
Mark as Played
September 26, 2025 • 19 mins
Cross-posted from my Substack
To start off with, I’ve been vegan/vegetarian for the majority of my life.
I think that factory farming has caused more suffering than anything humans have ever done.
Yet, according to my best estimates, I think most animal-lovers should eat meat.
Here's why:
To start off with, I’ve been vegan/vegetarian for the majority of my life.
I think that factory farming has caused more suffering than anything humans have ever done.
Yet, according to my best estimates, I think most animal-lovers should eat meat.
Here's why:
- It is probably unhealthy to be vegan. This affects your own well-being and your a...
Mark as Played
This is a link post. Today, the Global Call for AI Red Lines was released and presented at the UN General Assembly. It was developed by the French Center for AI Safety, The Future Society and the Center for Human-compatible AI. This call has been signed by a historic coalition of 200+ former heads of state, ministers, diplomats, Nobel laureates, AI pioneers, scientists, human rights advocates, political leaders, and other influenti...
Mark as Played
September 22, 2025 • 4 mins
This is a review of the reviews, a meta review if you will, but first a tangent. and then a history lesson. This felt boring and obvious and somewhat annoying to write, which apparently writers say is a good sign to write about the things you think are obvious. I felt like pointing towards a thing I was noticing, like 36 hours ago, which in internet speed means this is somewhat cached. Alas.
I previously rode a motorcyc...
I previously rode a motorcyc...
Mark as Played
September 21, 2025 • 28 mins
I'm annoyed by various people who seem to be complaining about the book title being "unreasonable" – who don't merely disagree with the title of "If Anyone Builds It, Everyone Dies", but, think something like: "Eliezer and Nate violated a Group-Epistemic-Norm with the title and/or thesis."
I think the title is reasonable.
I think the title is probably true – I'm le...
I think the title is reasonable.
I think the title is probably true – I'm le...
Mark as Played
September 21, 2025 • 10 mins
TL;DR
Most “AGI ban” proposals define AGI by outcome: whatever potentially leads to human extinction. That's legally insufficient: regulation has to act before harm occurs, not after.
Most “AGI ban” proposals define AGI by outcome: whatever potentially leads to human extinction. That's legally insufficient: regulation has to act before harm occurs, not after.
- Strict liability is essential. High-stakes domains (health & safety, product liability, export controls) already impose liability for risky precursor states, not outcomes or intent. AGI regulation must do the same.
- F...
Mark as Played
Popular Podcasts
My Favorite Murder is a true crime comedy podcast hosted by Karen Kilgariff and Georgia Hardstark. Each week, Karen and Georgia share compelling true crimes and hometown stories from friends and listeners. Since MFM launched in January of 2016, Karen and Georgia have shared their lifelong interest in true crime and have covered stories of infamous serial killers like the Night Stalker, mysterious cold cases, captivating cults, incredible survivor stories and important events from history like the Tulsa race massacre of 1921. My Favorite Murder is part of the Exactly Right podcast network that provides a platform for bold, creative voices to bring to life provocative, entertaining and relatable stories for audiences everywhere. The Exactly Right roster of podcasts covers a variety of topics including historic true crime, comedic interviews and news, science, pop culture and more. Podcasts on the network include Buried Bones with Kate Winkler Dawson and Paul Holes, That's Messed Up: An SVU Podcast, This Podcast Will Kill You, Bananas and more.
The latest news in 4 minutes updated every hour, every day.
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Listen to 'The Bobby Bones Show' by downloading the daily full replay.