PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

37:45

“Fighting Obvious Nonsense About AI Diffusion” by Zvi

LessWrong (30+ Karma) ·

2025/05/14

Our government is determined to lose the AI race in the name of winning the AI race.The least we can do, if prioritizing winning the race, is to try and actually win it. It is one thing to prioritize ‘winning the AI race’ against China over ensuring that humanity survives, controls and can collectively steer our future. I disagree with that choice, but I understand it. This mistake is very human. I also believe that more alignment and security efforts at anything like current margins not only

en-gb

9:02

“Dodging systematic human errors in scalable...

LessWrong (30+ Karma) ·

2025/05/14

Audio note: this article contains 59 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Summary: Both our (UK AISI's) debate safety case sketch and Anthropic's research agenda point at systematic human error as a weak point for debate. This post talks through how one might strengthen a debate protocol to partially mitigate this. Not too many errors in unknown places The complexity theory models of debate assume some

en-gb

6:43

“Eliezer and I wrote a book: If Anyone Builds It,...

LessWrong (30+ Karma) ·

2025/05/14

Eliezer and I wrote a book. It's titled If Anyone Builds It, Everyone Dies. Unlike a lot of other writing either of us have done, it's being professionally published. It's hitting shelves on September 16th. It's a concise (~60k word) book aimed at a broad audience. It's been well-received by people who received advance copies, with some endorsements including: The most important book I've read for years: I want to bring it to every political and corporate leader in the world and stand over them

en-gb

13:03

“The Best Reference Works for Every Subject” by...

LessWrong (30+ Karma) ·

2025/05/14

Introduction The Best Textbooks on Every Subject is the Schelling point for the best textbooks on every subject. My The Best Tacit Knowledge Videos on Every Subject is the Schelling point for the best tacit knowledge videos on every subject. This post is the Schelling point for the best reference works for every subject. Reference works provide an overview of a subject. Types of reference works include charts, maps, encyclopedias, glossaries, wikis, classification systems, taxonomies, syllabi, and

en-gb

4:12

“LessWrong Community Weekend - Applications are open”...

LessWrong (30+ Karma) ·

2025/05/14

We are open for Applications: https://airtable.com/appkj2FkJDGMtM2MA/pagiUldderZqbuBaP/form >>> All infos on the main event page <<< Please help spread the word! Join the 12th Less Wrong Community Weekend (LWCW) in Berlin. This is among the largest rationalist social gatherings which brings together 250+ aspiring rationalists from across Europe and beyond for 4 days of intellectual exploration, socialising and fun. We will be taking over the whole hostel with a huge variety of

en-gb

7:34

“Working through a small tiling result” by James Payor

LessWrong (30+ Karma) ·

2025/05/14

Audio note: this article contains 154 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. tl;dr it seems that you can get basic tiling to work by proving that there will be safety proofs in the future, rather than trying to prove safety directly. This is not a new idea, e.g. here is Giles saying it 13 years ago. But this seems to me like it's relevant to a general answer for tiling, and I'd appreciate engagement,

en-gb

0:30

[Linkpost] “October The First Is Too Late” by gwern

LessWrong (30+ Karma) ·

2025/05/14

This is a link post. Clarity didn't work, trying mysterianism ---First published: May 13th, 2025 Source: https://www.lesswrong.com/posts/ZK4s5kB6YBhsHrNHf/october-the-first-is-too-late Linkpost URL:https://gwern.net/fiction/october --- Narrated by TYPE III AUDIO.

en-gb

8:20

“Too Soon” by Gordon Seidoh Worley

LessWrong (30+ Karma) ·

2025/05/13

It was a cold and cloudy San Francisco Sunday. My wife and I were having lunch with friends at a Korean cafe. My phone buzzed with a text. It said my mom was in the hospital. I called to find out more. She had a fever, some pain, and had fainted. The situation was serious, but stable. Monday was a normal day. No news was good news, right? Tuesday she had seizures. Wednesday she was in the ICU. I caught the first flight to Tampa. Thursday she rested comfortably. Friday she was diagnosed with

en-gb

2:12

“No-self as an alignment target” by Milan W

LessWrong (30+ Karma) ·

2025/05/13

Being a coherent and persistent agent with persistent goals is a prerequisite for long-horizon power-seeking behavior. Therefore, we should prevent models from representing themselves as coherent and persistent agents with persistent goals. If an LLM-based agent sees itself as ceasing to exist after each <endoftext> token and yet keeps outputting <endoftext> when appropriate, it will not resist shutdown. Therefore, we should make sure LLMs consistently behave as if they were

en-gb

13:06

“AI Doomerism in 1879” by David Gross

LessWrong (30+ Karma) ·

2025/05/13

I’m reading George Eliot's Impressions of Theophrastus Such (1879)—so far a snoozer compared to her novels. But chapter 17 surprised me for how well it anticipated modern AI doomerism. In summary, Theophrastus is in conversation with Trost, who is an optimist about the future of automation and how it will free us from drudgery and permit us to further extend the reach of the most exalted human capabilities. Theophrastus is more concerned that automation is likely to overtake, obsolete, and atrophy

en-gb

27:16

“Political sycophancy as a model organism of...

LessWrong (30+ Karma) ·

2025/05/12

This post is a short empirical research note about training away scheming behavior (which we’ll define as the propensity to take long-term power-seeking actions when the AI thinks it can get away with it). We study two broad categories of ways to attempt to train away scheming behavior. First, you can adversarially train, searching for realistic honeypots that cause the AI to take misaligned actions and then training the AI not to. Second, you can do normal alignment training, reinforcing the AI's

en-gb

5:18

[Linkpost] “Main Insights From The SB-1047...

LessWrong (30+ Karma) ·

2025/05/12

This is a link post. Last week I published a 30-minute documentary about SB-1047 I had been working on since September. Here's what I learned. Story of the bill The bill had to go through many committees before passing the California Senate and Assembly, eventually reaching the Governor's desk Most people started paying attention in May-Sep 2024, but the story of the bill starts in September 2023, when Senator Scott Wiener published an intent bill to gather support (co-sponsors), before

en-gb

4:35

“PSA: The LessWrong Feedback Service” by JustisMills

LessWrong (30+ Karma) ·

2025/05/12

At the bottom of the LessWrong post editor, if you have at least 100 global karma, you may have noticed this button.The button Many people click the button, and are jumpscared when it starts an Intercom chat with a professional editor (me), asking what sort of feedback they'd like. So, that's what it does. It's a summon Justis button. Why summon Justis? To get feedback on your post, of just about any sort. Typo fixes, grammar checks, sanity checks, clarity checks, fit for LessWrong, the works. If

en-gb

6:46

“AIs at the current capability level may be important...

LessWrong (30+ Karma) ·

2025/05/12

Sometimes people say that it's much less valuable to do AI safety research today than it will be in the future, because the current models are very different—in particular, much less capable—than the models that we're actually worried about. I think that argument is mostly right, but it misses a couple of reasons models as capable as current models might still be important at the point where AI is posing substantial existential risk. In this post, I'll describe those reasons. Our best trusted

en-gb

65:07

“Highly Opinionated Advice on How to Write ML Papers”...

LessWrong (30+ Karma) ·

2025/05/12

TL;DR The essence of an ideal paperis the narrative: a short, rigorous and evidence-based technical story you tell, with a takeaway the readers care about What? A narrative is fundamentally about a contribution to our body of knowledge: one to three specific novel claimsthat fit within a cohesive theme How? You need rigorous empirical evidence that convincingly supports your claims So what? Why should the reader care? What is the motivation, the problem you’re trying to solve, the way it all

en-gb

21:39

“a confusion about preference orderings” by...

LessWrong (30+ Karma) ·

2025/05/11

Here's a confusion I have about preference orderings in decision theory. Caveat: the observations I make below feel weirdly trivial to me, to the point that I feel wary of making a post about them at all; the specter of readers rolling their eyes and thinking "oh he's just talking about X in a really weird way" looms large in my mind as I type. It feels like I'm probably just unaware of some standard term or concept in the literature, which would make everything "snap into place" if I knew about

en-gb

5:21

“Better Air Purifiers” by jefftk

LessWrong (30+ Karma) ·

2025/05/11

Are you looking for a project where you could substantially improveindoor air quality, with benefits both to general health and reducing pandemic risk? I've written a bunch about air purifiers over the past few years, and its frustrating how bad commercial market is. The most glaring problem is the widespread use of HEPA filters. These are very effective filters that, unavoidably, offer significant resistance to air flow. HEPA is a great option for filtering air in single pass, such

en-gb

9:44

“Glass box learners want to be black box” by Cole Wyeth

LessWrong (30+ Karma) ·

2025/05/11

Epistemic status: intuitive speculation with scattered mathematical justification. My goal here is to interrogate the dream of writing a beautiful algorithm for intelligence and thereby ensuring safety. For example: I don't know precisely what alternative he had in mind, but I only seem to remember reading clean functional programs from MIRI, so that is one possibility. Whether or not anyone else endorses it, that is the prototypical picture I have in mind as the holy grail of glass box AGI

en-gb

5:51

“It’s Okay to Feel Bad for a Bit” by moridinamael

LessWrong (30+ Karma) ·

2025/05/11

"If you kiss your child, or your wife, say that you only kiss things which are human, and thus you will not be disturbed if either of them dies." - Epictetus "Whatever suffering arises, all arises due to attachment; with the cessation of attachment, there is the cessation of suffering." - Pali canon "He is not disturbed by loss, he does not delight in gain; he is not disturbed by blame, he does not delight in praise; he is not disturbed by pain, he does not delight in pleasure; he is not disturbed

en-gb

2:02

“Consider not donating under $100 to political...

LessWrong (30+ Karma) ·

2025/05/11

Epistemic status: thing people have told me that seems right. Also primarily relevant to US audiences. Also I am speaking in my personal capacity and not representing any employer, present or past. Sometimes, I talk to people who work in the AI governance space. One thing that multiple people have told me, which I found surprising, is that there is apparently a real problem where people accidentally rule themselves out of AI policy positions by making political donations of small amounts—in

en-gb

4,489 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Talking Tech w/ Wayne

Wayne Hunter

The Everything Feed - All Packet Pushers Pods

Packet Pushers

The Good Tech Companies

HackerNoon

Engadget News + Next

Engadget

Cybersecurity Tech Brief By HackerNoon

HackerNoon