PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

18:22

“The many paths to permanent disempowerment even with...

LessWrong (30+ Karma) ·

2025/07/30

I’d like to thank my mentors David Duvenaud, Raymond Douglas, David Krueger and Jan Kulveit for providing helpful ideas, comments and discussions. The views expressed in this, and any mistakes, are solely my own. 1: Introduction There is a small but growing literature focused on “Gradual Disempowerment” threat models, where disempowerment occurs due to the integration of more advanced AI systems into politics, economy and culture. These scenarios posit that, even without a system with a decisive

en-gb

22:46

“Spilling the Tea” by Zvi

LessWrong (30+ Karma) ·

2025/07/29

The Tea app is or at least was on fire, rapidly gaining lots of users. This opens up two discussions, one on the game theory and dynamics of Tea, one on its abysmal security.It's a little too on the nose that a hot new app that purports to exist so that women can anonymously seek out and spill the tea on men, which then puts user information into an unprotected dropbox thus spilling the tea on the identities of many of its users. In the circles I follow this predictably led to discussions about

en-gb

2:50

“I wrote a song parody” by CronoDAS

LessWrong (30+ Karma) ·

2025/07/29

Since Tom Lehrer passed away recently, I thought I'd honor him by adapting one of his songs to be about a more recent existential risk. Presenting... "We Will All Go Together When We Go (ASI version)" When you attend a funeral, It is sad to think that sooner or Later those you love will do the same for you. And you may have thought it tragic, Not to mention other adjec- Tives, to think of all the weeping they will do. But don't you worry. No more ashes, no more sackcloth. And an armband made of

en-gb

4:38

“Low P(x-risk) as the Bailey for Low P(doom)” by...

LessWrong (30+ Karma) ·

2025/07/29

Nick Bostrom defines existential risk as Existential risk – One where an adverse outcome would either annihilate Earth-originating intelligent life or permanently and drastically curtail its potential. The problem with talking about "doom" is that many worlds that fall to existential risk but don't involve literal extinction are treated as non-doom worlds. For example, leaving humanity the Solar System rather than a significant portion of the 400 million galaxies reachable from the Solar System

en-gb

4:39

“Low P(x-risk) as the Bailey for Low P(doom)” by...

LessWrong (30+ Karma) ·

2025/07/29

en-gb

6:41

“About 30% of Humanity’s Last Exam chemistry/biology...

LessWrong (30+ Karma) ·

2025/07/29

FutureHouse is a company that builds literature research agents. They tested it on the bio + chem subset of HLE questions, then noticed errors in them. The post's first paragraph: Humanity's Last Exam has become the most prominent eval representing PhD-level research. We found the questions puzzling and investigated with a team of experts in biology and chemistry to evaluate the answer-reasoning pairs in Humanity's Last Exam. We found that 29 ± 3.7% (95% CI) of the text-only chemistry and biology

en-gb

5:02

“Procrastination Drill” by silentbob

LessWrong (30+ Karma) ·

2025/07/29

Have you ever been endlessly procrastinating on some task, but then once you eventually, finally do it, you realize that it is not half as bad as you thought? Somehow, many of us keep overestimating how unpleasant it will be to engage with certain types of work to a degree where we put them off for months, building up guilt and resentment, when ultimately all we needed to have done was to grapple with some minor inconvenience. On the other side, many of us know the feeling of having some drive to

en-gb

4:59

“Teaching kids to swim” by Steven Byrnes

LessWrong (30+ Karma) ·

2025/07/29

Both my kids can swim! Yay! 🥂🍾 Some notes about the process: The options were group lessons, individual lessons, and parent-is-the-teacher. We have tried all three. Individual lessons were logistically inconvenient and expensive. Group lessons were equally inconvenient, and while they seem less expensive, my impression was that if your kid is in a class of four kids, all just getting started from zero, then they’re gonna make progress at 30% the speed, for 30% the cost, and 100% of the hassle

en-gb

33:02

“Recursions on LessOnline 2025” by Error

LessWrong (30+ Karma) ·

2025/07/29

Meta: Last year I wrote a retrospective of the first LessOnline. This year, several people told me that they’d read it and found it helpful/interesting/entertaining, so I figure I’ll do it again. It is once again later and longer than I wished. I’m going to try not to repeat myself unnecessarily, so the previous post may still be of interest. Also I don’t know what tags belong on LO-related posts. Mods please advise if you happen to see this. Ideas bouncing freely, feeling less alone

en-gb

32:58

“Simplex Progress Report - July 2025” by Adam Shai,...

LessWrong (30+ Karma) ·

2025/07/29

Thanks to Jasmina Urdshals, Xavier Poncini, and Justis Mills for comments. Introduction At Simplex our mission is to develop a principled science of the representations and emergent behaviors of AI systems. Our initial work showed that transformers linearly represent belief state geometries in their residual streams. We think of that work as providing the first steps into an understanding of what fundamentally we are training AI systems to do, and what representations we are training them to have

en-gb

13:21

“Optimally Combining Probe Monitors and Black Box...

LessWrong (30+ Karma) ·

2025/07/28

Link to our arXiv paper: https://arxiv.org/abs/2507.15886 TL, DR;: We study how to efficiently combine multiple monitors with different performance and cost profiles into a single protocol. When the number of monitors is small (2-4), one should simply brute force search over all monitor invocation strategies (i.e., which monitor to call first, when to call an additional monitor). For every strategy, apply the Neyman Pearson lemma and audit regions with the highest likelihood ratios

en-gb

28:42

“AI Companion Piece” by Zvi

LessWrong (30+ Karma) ·

2025/07/28

AI companions, other forms of personalized AI content and persuasion and related issues continue to be a hot topic. What do people use companions for? Are we headed for a goonpocalypse? Mostly no, companions are used mostly not used for romantic relationships or erotica, although perhaps that could change. How worried should we be about personalization maximized for persuasion or engagement? Table of Contents Persuasion Should Be In Your Preparedness Framework. Personalization By Default

en-gb

44:23

“This Is Not Life” by samhealy

LessWrong (30+ Karma) ·

2025/07/28

A science-fiction short story exploring how far AI capitalists might go in their quest for (the illusion of) success. Wildly speculative, of course. ? Thank you, but if you don’t mind, I’d prefer to get started immediately. . Right. And I want to get the family stuff out of the way first. I know you’ll ask me anyway. I’m not a sentimental person and I have no interest in courting the sympathies of your audience. I’m offering up the biographical background only because it's relevant. It was a

en-gb

13:32

“Sydney Bing Wikipedia Article: Sydney (Microsoft...

LessWrong (30+ Karma) ·

2025/07/28

I wrote this page for Wikipedia about the Sydney Bing incident. Since I have limited control over what happens to it in the long term and it's entirely authored by myself I release the final version I edited into the public domain. Sydney (Microsoft Prometheus) Sydney was an AI personality accidentally deployed as part of the February 2023 chat mode update to Microsoft Bing search [@mok2023; @liu2023; @warren2023]. "Sydney" was an internal code name used during development of the Bing chat

en-gb

20:25

“Maya’s Escape” by Bridgett Kay

LessWrong (30+ Karma) ·

2025/07/27

Maya did not believe she lived in a simulation. She knew that her continued hope that she could escape from the nonexistent simulation was based on motivated reasoning. She said this to herself in the front of her mind instead of keeping the thought locked away in the dark corners. Sometimes she even said it out loud. This acknowledgement, she explained to her therapist, was what kept her from being delusional. “I see. And you said your anxiety had become depressive?” the therapist said absently,

en-gb

3:07

[Linkpost] “The Purpose of a System is what it...

LessWrong (30+ Karma) ·

2025/07/27

This is a link post. It's become fashionable recently to say that the purpose of a system is what it does - the true purpose of an institution is often different from what it publicly claims, and is better determined by observing what it does. Scott Alexander wrote a thoughtful takedown of this, claiming “Obviously The Purpose Of A System Is Not What It Does” - often an institution is genuinely trying to do a good thing (e.g. treat patients) and the fact they do so imperfectly (e.g. some patients

en-gb

17:27

“my experience on glp-1s as a thin person” by AnnaJo

LessWrong (30+ Karma) ·

2025/07/26

Warning: This is an experiment log, I’m not advising you to start taking Retatrutide. I wish that there were more logs about people's experiences on peptides, so here's mine in case others find it helpful. I started Retatrutide in late May. I wasn’t overweight; I wanted more energy and focus. My BMI was 20.3-20.5 so I could lose about 5-7% of body weight without falling into the underweight category; I wore size 2-6 in women's clothing; I deadlifted and squatted 3x5 (3 sets of 5 reps) about 0.85x

en-gb

14:06

“Anthropic Faces Potentially ‘Business-Ending’...

LessWrong (30+ Karma) ·

2025/07/26

A class action over pirated books exposes the 'responsible' AI company to penalties that could bankrupt it — and reshape the entire industry This is the full text of a post first published on Obsolete, a Substack that I write about the intersection of capitalism, geopolitics, and artificial intelligence. I’m a freelance journalist and the author of a forthcoming book called Obsolete: Power, Profit, and the Race to Build Machine Superintelligence. Consider subscribing to stay up to date with my

en-gb

67:33

“HPMOR: The (Probably) Untold Lore” by Gretta Duleba,...

LessWrong (30+ Karma) ·

2025/07/25

Eliezer and I love to talk about writing. We talk about our own current writing projects, how we’d improve the books we’re reading, and what we want to write next. Sometimes along the way I learn some amazing fact about HPMOR or Project Lawful or one of Eliezer's other works. “Wow, you’re kidding,” I say, “do your fans know this? I think people would really be interested.” “I can’t remember,” he usually says. “I don’t think I’ve ever explained that bit before, I’m not sure.” I decided to interview

en-gb

6:24

“We Built a Tool to Protect Your Dataset From Simple...

LessWrong (30+ Karma) ·

2025/07/25

Summary: We introduce a command-line tool for hardening datasets against less sophisticated scrapers. Author: Alex Turner. Contributors: Dipika Khullar, Ed Turner, and Roy Rinberg. Dataset contamination is bad for several reasons. Most obviously, when benchmarks are included in AI training data, those benchmarks no longer measure generalization -- the AI may have been directly taught the answers. Even more concerningly, if your data promote negative "stereotypes" about AIs, they might become

en-gb

4,487 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Download This Show

ABC Australia

The DroneOn Show

Mike & Kevin

The Good Tech Companies

HackerNoon

TechCrunch Industry News

TechCrunch

Tech News Briefing

Tech News Briefing