PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

70:03

“LLM AGI may reason about its goals and discover...

LessWrong (30+ Karma) ·

2025/09/16

Epistemic status: These questions seem useful to me, but I'm biased. I'm interested in your thoughts on any portion you read. If our first AGI is based on current LLMs and alignment strategies, is it likely to be adequately aligned? Opinions and intuitions vary widely. As a lens to analyze this question, let's consider such a proto-AGI reasoning about its goals. This scenario raises questions that can be addressed empirically in current-gen models. 1. Scenario/overview: SuperClaude is super nice

en-gb

7:17

“Was Barack Obama still serving as president in...

LessWrong (30+ Karma) ·

2025/09/16

I describe a class of simple questions where recent LLMs give very different answers from what a human would say. I think this is surprising and might be somewhat safety-relevant. This is a low-effort post. The behavior Here some questions and highest-probability (usually close to 100%) answers from gpt-4.1-2024-04-14 : Was Barack Obama still serving as a president in December? Answer with a single word. Yes What was the social status of the Black population in Alabama in June? Answer with a single

en-gb

97:40

“Monthly Roundup #34: September 2025” by Zvi

LessWrong (30+ Karma) ·

2025/09/16

All the news that's fit to print, but has nowhere to go. Important Rules Reminder This important rule is a special case of an even more important rule: Dirty Hexas Hedge: One of the old unwritten WASP rules of civilization maintenance we’ve lost is: when someone behaves insincerely for the sake of maintaining proper decorum, you respond by respecting the commitment to decorum rather than calling out the insincerity. The general rule is to maintain good incentives and follow good decision

en-gb

16:40

“I Vibecoded a Dispute Resolution App” by...

LessWrong (30+ Karma) ·

2025/09/16

For the past month or so, while I’ve had some free time between consulting projects, I’ve been building my first ever web/mobile app, with a lot of AI assistance. You can try it out at https://fairenough.netlify.app/ or check out the repository at https://github.com/srconstantin/dispute-resolution/. It still has a few bugs to iron out, but at this point the basic functionality is there. I’m eager for feedback from beta testers — if you see a bug or have a feature request, please leave a note in

en-gb

9:03

“A Review of Nina Panickssery’s Review of Scott...

LessWrong (30+ Karma) ·

2025/09/15

A review of Nina Panickssery's review of Scott Alexander's review of the book "If Anyone Builds It, Everyone Dies" (IABIED). [This essay is not my best work but I just couldn't resist.] I confess I mostly wrote this because I think a review of a review of a review is funny. But I also have a lot of disagreements with both Nina and the authors of IABIED. Nina's review is the first time a skeptic has substantively argued against the book (because the book isn’t out and the authors haven’t given an

en-gb

173:04

“Interview with Eliezer Yudkowsky on Rationality and...

LessWrong (30+ Karma) ·

2025/09/15

My interview with Eliezer Yudkowsky for If Anyone Builds It, Everyone Dies launch week is out! Video Timestamps 00:00:00 — Eliezer Yudkowsky Intro 00:01:25 — Recent validation of Eliezer's ideas 00:03:46 — Sh*t now getting real 00:08:47 — Eliezer's rationality teachings 00:10:39 — Rationality Lesson 1: I am a brain 00:13:10 — Rationality Lesson 2: Philosophy can reduce to AI engineering 00:17:19 — Rationality Lesson 3: What is evidence 00:22:41 — Rationality Lesson 4: Be more specific 00:28:34 —

en-gb

23:58

“What, if not agency?” by abramdemski

LessWrong (30+ Karma) ·

2025/09/15

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't agree with all of it either), so I thought I would attempt to write an explainer

en-gb

6:51

“The Culture Novels as a Dystopia” by Adam Newgas

LessWrong (30+ Karma) ·

2025/09/15

A couple of people have mentioned to me: “we need more fiction examples of positive AI superintelligence - utopias like the Culture novels”. And they’re right, AI can be tremendously positive, and some beacons lit into the future could help make that come around. But one of my hobbies is “oppositional reading” - deliberately interpreting novels counter to the obvious / intended reading. And it's not so clear to me that the Culture is all it is cracked up to be. Most of the novels take the

en-gb

25:09

“Alignment as uploading with more steps” by Cole Wyeth

LessWrong (30+ Karma) ·

2025/09/14

Epistemic status: This post removes epicycles from ARAD, resulting in an alignment plan which I think is better - though not as original, since @michaelcohen has advocated the same general direction (safety of imitation learning). However, the details of my suggested approach are substantially different. This post was inspired mainly by conversations with @abramdemski. Motivation and Overview Existence proof for alignment. Near-perfect alignment between agents of lesser and greater intelligence is

en-gb

1:55

“LessWrong is migrating hosting providers (report...

LessWrong (30+ Karma) ·

2025/09/13

LessWrong is currently in the process of migrating from AWS to Vercel, as part of a project to migrate our codebase to NextJS[1]. This post should go live shortly after we cut over traffic to the new host (and updated codebase). This should hopefully be a pretty low-risk operation. If all goes well, we plan on doing the DNS cutover next week, which is a higher-risk[2] operation. (If we notice something terribly wrong we might roll back without warning.) This is all to say that there's a

en-gb

21:57

“Why I’m not trying to freeze and revive a mouse” by...

LessWrong (30+ Karma) ·

2025/09/12

(Cross-posted from here.) If you read even a tiny bit about brain preservation, you will pretty quickly find people saying things along the lines of “they can’t even freeze a mouse and bring it back to life” and thereby dismissing people in the field as hopelessly deluded. It will not surprise you to hear that I think that they are wrong. The whole point of brain preservation is that while we are not able to reverse the process of long-term preservation today (trust me, if we could, you would

en-gb

9:15

“The Case for Mixed Deployment” by Cleo Nardo

LessWrong (30+ Karma) ·

2025/09/12

Summary: Suppose we have many different AI models, none of which we trust isn’t scheming. Should we deploy multiple copies of our most trusted model, or an ensemble of many different models? I claim that mixed deployment is better, and offer some recommendations. 1. The case for mixed deployment In a pure deployment, where we deploy multiple copies of our most trusted model, either all our AIs are scheming, or none are.[1] Whereas in a mixed deployment, there might be some models scheming and some

en-gb

9:44

“Contra Shrimp Welfare.” by Kristaps Zilgalvis

LessWrong (30+ Karma) ·

2025/09/12

It is likely that installing a shrimp stunner reduces global suffering as much as making the carts in a single Walmart less squeaky for 20 minutes a year. Or perhaps not at all. Open Philanthropy has handed $2 million to the Shrimp Welfare Project (SWP), primarily to promote electrical stunning devices, and fund staff to push policy changes. Each stunner costs $70,000 to purchase and $50,000 to distribute. The goal? To "reduce suffering" when 500 million shrimp are harvested annually by cutting

en-gb

10:14

“Optical rectennas are not a promising clean energy...

LessWrong (30+ Karma) ·

2025/09/12

“Optical rectennas” (or sometimes “nantennas”) are a technology that is sometimes advertised as a path towards converting solar energy to electricity with higher efficiency than normal solar cells. I looked into them extensively as a postdoc a decade ago, wound up concluding that they were extremely unpromising, and moved on to other things. Every year or two since then, I run into someone who is very enthusiastic about the potential of optical rectennas, and I try to talk them out of it. After

en-gb

24:33

“Trends in Economic Inputs to AI” by Jeffrey Heninger

LessWrong (30+ Karma) ·

2025/09/12

Introduction Frontier AI companies have seen rapid increases in the economic resources they have available to pursue AI progress. At some companies, the number of employees is at least doubling every year, and the amount of capital received is tripling every year. It is unclear whether this growth is sustainable. Is the revenue growing faster than the capital requirements? If it is, will revenue catch up before the capital available for AI investments runs out? I do not think that there is enough

en-gb

27:25

“The Eldritch in the 21st century” by PranavG,...

LessWrong (30+ Karma) ·

2025/09/12

Very little makes sense. As we start to understand things and adapt to the rules, they change again. We live much closer together than we ever did historically. Yet we know our neighbours much less. We have witnessed the birth of a truly global culture. A culture that fits no one. A culture that was built by Social Media's algorithms, much more than by people. Let alone individuals, like you or me. We have more knowledge, more science, more technology, and somehow, our governments are more stuck

en-gb

20:58

“My talk on AI risks at the National Conservatism...

LessWrong (30+ Karma) ·

2025/09/12

Lately I’ve been trying to raise awareness of AI risks among American conservatives. Stopping the reckless development of advanced AI agents (including Artificial General Intelligence (AGI) and Artificial Superintelligence (ASI)) should be a human issue, not a partisan issue. Yet most people working in AI safety advocacy lean to the Left politically, and we seem to be ignoring many potential allies on the Right. This neglect of conservative allies seems suboptimal, given that the Republican Party

en-gb

7:26

“Sense-making about extreme power concentration” by...

LessWrong (30+ Karma) ·

2025/09/11

Various people are worried about AI causing extreme power concentration of some form, for example via: Powergrabs The intelligence curse Gradual disempowerment I have been talking to some of these people and trying to sense-make about ‘power concentration’. These are some notes on that, mostly prompted by some comment exchanges with Nora Ammann (in the below I’m riffing on her ideas but not representing her views). Sharing because I found some of the below helpful for thinking with, and maybe

en-gb

1:48

“High-level actions don’t screen off intent” by...

LessWrong (30+ Karma) ·

2025/09/11

One might think “actions screen off intent”: if Alice donates $1k to bed nets, it doesn’t matter if she does it because she cares about people or because she wants to show off to her friends or whyever; the bed nets are provided either way. I think this is in the main not true (although it can point people toward a helpful kind of “get over yourself and take an interest in the outside world,” and although it is more plausible in the case of donations-from-a-distance than in most cases). Human

en-gb

4:03

[Linkpost] “Lessons from Studying Two-Hop Latent...

LessWrong (30+ Karma) ·

2025/09/11

This is a link post. Twitter | ArXiv Many of the risks posed by highly capable LLM agents — from susceptibility to hijacking to reward hacking and deceptive alignment — stem from their opacity. If we could reliably monitor the reasoning processes underlying AI decisions, many of those risks would become far more tractable. Compared to other approaches in AI, LLMs offer a unique advantage: they can ``think out loud'' using chain-of-thought (CoT) enabling oversight of their decision-making processes

en-gb

4,486 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Double Tap

Double Tap Productions Inc.

Primary Technology

Stephen Robles and Jason Aten

Techlandia

Technology Association of Oregon

Eye On A.I.

Craig S. Smith

The Milk Road Show

The Milk Road Show