PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

18:23

“Boots theory and Sybil Ramkin” by philh

LessWrong (30+ Karma) ·

2025/03/19

I previously wrote about Boots theory, the idea that "the rich are so rich because they spend less money". My one-sentence take is: I'm pretty sure rich people spend more money than poor people, and an observation can't be explained by a falsehood. The popular explanation of the theory comes from Sam Vimes, a resident of Ankh-Morpork on the Discworld (which is carried on the backs of four elephants, who themselves stand on a giant turtle swimming through space). I claim that Sam Vimes doesn't have

en-gb

9:56

“LessOnline 2025: Early Bird Tickets On Sale” by Ben...

LessWrong (30+ Karma) ·

2025/03/18

Our festival of truthseeking and blogging is happening again this year. It's from Friday May 30th to Sunday June 1st at Lighthaven (Berkeley, CA). Early bird pricing is currently at $450 until the end of the month. You can buy tickets and learn more at the website: Less.Online FAQ Who should come?If you check LessWrong, or read any sizeable number of the bloggers invited, I think you will probably enjoy being here at LessOnline, sharing ideas and talking to bloggers you read. What happened last

en-gb

10:08

“I changed my mind about orca intelligence” by...

LessWrong (30+ Karma) ·

2025/03/18

TLDR: I now think it's <1% likely that average orcas are >=+6std intelligent.(I now think the relevant question is rather whether orcas might be >=+4std intelligent, since that might be enough for superhuman wisdom and thinking techniques to accumulate through generations, but I think it's only 2% probable. (Still decently likely that they are near human level smart though.))1. Insight: Think about societies instead of individualsI previously thought of +7std orcas like having +7std

en-gb

11:13

“Go home GPT-4o, you’re drunk: emergent misalignment...

LessWrong (30+ Karma) ·

2025/03/18

Replicating the Emergent Misalignment model suggests it is unfiltered, not unalignedWe were very excited when we first read the Emergent Misalignment paper. It seemed perfect for AI alignment. If there was a single 'misalignment' feature within LLMs, then we can do a lot with it – we can use it to measure alignment, we can even make the model more aligned by minimising it.What was so interesting, and promising, was that finetuning a model on a single type of misbehaviour seemed to cause general

en-gb

12:35

“OpenAI #11: America Action Plan” by Zvi

LessWrong (30+ Karma) ·

2025/03/18

OpenAI Tells Us Who They AreLast week I covered Anthropic's submission to the request for suggestions for America's action plan. I did not love what they submitted, and especially disliked how aggressively they sidelines existential risk and related issues, but given a decision to massively scale back ambition like that the suggestions were, as I called them, a ‘least you can do’ agenda, with many thoughtful details. OpenAI took a different approach. They went full jingoism in the first

en-gb

17:04

“Feedback loops for exercise (VO2Max)” by Elizabeth

LessWrong (30+ Karma) ·

2025/03/18

The perfect exercise doesn’t exist. The good-enough exercise is anything you do regularly without injuring yourself. But maybe you want more than good enough. One place you could look for insight is studies on how 20 college sophomores responded to a particular 4 week exercise program, but you will be looking for a long time. What you really need are metrics that help you fine tune your own exercise program. VO2max (a measure of how hard you are capable of performing cardio) is a promising

en-gb

1:05

“FrontierMath Score of o3-mini Much Lower Than...

LessWrong (30+ Karma) ·

2025/03/18

OpenAI reports that o3-mini with high reasoning and a Python tool receives a 32% on FrontierMath. However, Epoch's official evaluation[1] received only 11%. There are a few reasons to trust Epoch's score over OpenAIs: Epoch built the benchmark and has better incentives.OpenAI reported a 28% score on the hardest of the three problem tiers - suspiciously close to their overall score.Epoch has published quite a bit of information about its testing infrastructure and data, whereas OpenAI has published

en-gb

20:48

“Falsified draft: ‘Against Yudkowsky’s evolution...

LessWrong (30+ Karma) ·

2025/03/18

So here's a post I spent the past two months writing and rewriting. I abandoned this current draft after I found out that my thesis was empirically falsified three years ago by this paper, which provides strong evidence that transformers implement optimization algorithms internally. I'm putting this post up anyway as a cautionary tale about making clever arguments rather than doing empirical research. Oops. 1. OverviewThe first time someone hears Eliezer Yudkowsky's argument that AI will probably

en-gb

6:28

“Three Types of Intelligence Explosion” by...

LessWrong (30+ Karma) ·

2025/03/18

AbstractOnce AI systems can design and build even more capable AI systems, we could see an intelligence explosion, where AI capabilities rapidly increase to well past human performance.The classic intelligence explosion scenario involves a feedback loop where AI improves AI software. But AI could also improve other inputs to AI development. This paper analyses three feedback loops in AI development: software, chip technology, and chip production. These could drive three types of intelligence

en-gb

13:43

“Sentinel’s Global Risks Weekly Roundup #11/2025....

LessWrong (30+ Karma) ·

2025/03/18

Top items: Trump invoked the Alien Enemies Act against Venezuelans and the Tren de Aragua gang. He subsequently deported 238 alleged members to El Salvador, ignoring a court order.Chinese “invasion barges” were deployed in an exercise.The US resumed military aid to Ukraine, and a ceasefire in the next six months at 50/50 Forecaster EstimatesForecasters, on aggregate, think that a 30-day ceasefire in Ukraine in the next six months is a coin toss (48%, ranging from 35% to 70%). Polymarket's forecast

en-gb

16:24

“Notable utility-monster-like failure modes on...

LessWrong (30+ Karma) ·

2025/03/17

By Roland Pihlakas, Sruthi Kuriakose, Shruti Datta Gupta Summary and Key TakeawaysRelatively many past AI safety discussions have centered around the dangers of unbounded utility maximisation by RL agents, illustrated by scenarios like the "paperclip maximiser". Unbounded maximisation is problematic for many reasons. We wanted to verify whether these RL utility-monster problems are still relevant with LLMs as well. Turns out, strangely, this is indeed clearly the case. The problem is not that the

en-gb

18:06

“Claude Sonnet 3.7 (often) knows when it’s in...

LessWrong (30+ Karma) ·

2025/03/17

Note: this is a research note based on observations from evaluating Claude Sonnet 3.7. We’re sharing the results of these ‘work-in-progress’ investigations as we think they are timely and will be informative for other evaluators and decision-makers. The analysis is less rigorous than our standard for a published paper. Summary We monitor Sonnet's reasoning for mentions that it is in an artificial scenario or an alignment test. Claude Sonnet 3.7 appears to be aware of being tested for alignment

en-gb

4:26

“Metacognition Broke My Nail-Biting Habit” by Rafka

LessWrong (30+ Karma) ·

2025/03/17

BackgroundFor almost ten years, I struggled with nail biting—especially in moments of boredom or stress. I tried numerous times to stop, with at best temporary (one week) success. The techniques I tried ranged from just "paying attention" to punishing myself for doing it (this didn't work at all).Recently, I've been interested in metacognitive techniques, like TYCS. Inspired by this, I've succeeded in stopping this unintended behaviour easily and for good (so far).The technique is by no means

en-gb

25:24

“How I’ve run major projects” by benkuhn

LessWrong (30+ Karma) ·

2025/03/17

My few most productive individual weeks at Anthropic have all been “crisis project management:” coordinating major, time-sensitive implementation or debugging efforts. In a company like Anthropic, excellent project management is an extremely high-leverage skill, and not just during crises: our work has tons of moving parts with complex, non-obvious interdependencies and hard schedule constraints, which means organizing them is a huge job, and can save weeks of delays if done right. Although a lot of

en-gb

11:19

“Any-Benefit Mindset and Any-Reason Reasoning” by...

LessWrong (30+ Karma) ·

2025/03/16

One concept from Cal Newport's Deep Work that has stuck with me is that of the any-benefit mindset:To be clear, I’m not trying to denigrate the benefits [of social media]—there's nothing illusory or misguided about them. What I’m emphasizing, however, is that these benefits are minor and somewhat random. [...] To this observation, you might reply that value is value: If you can find some extra benefit in using a service like Facebook—even if it's small—then why not use it? I call this way of

en-gb

9:08

“Announcing EXP: Experimental Summer Workshop on...

LessWrong (30+ Karma) ·

2025/03/16

EXP is an experimental summer workshop combining applied rationality with immersive experiential education. We create a space where theory meets practice through simulated scenarios, games, and structured experiences designed to develop both individual and collective capabilities and virtues. Core Focus Areas Collective intelligence: How can groups think clearly together?Individual and group virtues: How can we trust ourselves and others?AI: How can current or future AI systems empower humans

en-gb

6:59

“Why White-Box Redteaming Makes Me Feel Weird” by...

LessWrong (30+ Karma) ·

2025/03/16

There's this popular trope in fiction about a character being mind controlled without losing awareness of what's happening. Think Jessica Jones, The Manchurian Candidate or Bioshock. The villain uses some magical technology to take control of your brain - but only the part of your brain that's responsible for motor control. You remain conscious and experience everything with full clarity.If it's a children's story, the villain makes you do embarrassing things like walk through the street naked, or

en-gb

2:18

“I make several million dollars per year and have...

LessWrong (30+ Karma) ·

2025/03/16

I have, over the last year, become fairly well-known in a small corner of the internet tangentially related to AI.As a result, I've begun making what I would have previously considered astronomical amounts of money: several hundred thousand dollars per month in personal income.This has been great, obviously, and the funds have alleviated a fair number of my personal burdens (mostly related to poverty). But aside from that I don't really care much for the money itself. My long term ambitions have

en-gb

34:08

“AI for AI safety” by Joe Carlsmith

LessWrong (30+ Karma) ·

2025/03/15

(Audio version here (read by the author), or search for "Joe Carlsmith Audio" on your podcast app. This is the fourth essay in a series that I’m calling “How do we solve the alignment problem?”. I’m hoping that the individual essays can be read fairly well on their own, but see this introduction for a summary of the essays that have been released thus far, and for a bit more about the series as a whole.) 1. Introduction and summaryIn my last essay, I offered a high-level framework for thinking about

en-gb

27:01

“On MAIM and Superintelligence Strategy” by Zvi

LessWrong (30+ Karma) ·

2025/03/15

Dan Hendrycks, Eric Schmidt and Alexandr Wang released an extensive paper titled Superintelligence Strategy. There is also an op-ed in Time that summarizes. The major AI labs expect superintelligence to arrive soon. They might be wrong about that, but at minimum we need to take the possibility seriously. At a minimum, the possibility of imminent superintelligence will be highly destabilizing. Even if you do not believe it represents an existential risk to humanity (and if so you are very wrong about

en-gb

4,491 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

The Automated Daily

TrendTeller

All On AI

All On AI

Elon Musk Podcast

Stage Zero

Reflections

Livewire Labs

科技早8点

之远不知远