PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

4:37

“D&D.Sci: The Mad Tyrant’s Pet Turtles” by...

LessWrong (30+ Karma) ·

2024/03/30

This is a D&D.Sci scenario: a puzzle where players are given a dataset to analyze and an objective to pursue using information from that dataset.You steel your nerves as the Mad Tyrant[1] peers at you from his throne. In theory, you have nothing to worry about: since the Ninety Degree Revolution last year, His Malevolence[2] has had his power sharply curtailed, and his bizarre and capricious behavior has shifted from homicidally vicious to merely annoying. So while everyone agrees he's still

en-gb

18:19

“SAE reconstruction errors are (empirically)...

LessWrong (30+ Karma) ·

2024/03/29

Summary. Sparse Autoencoder (SAE) errors are empirically pathological: when a reconstructed activation vector is distance <span>_epsilon_</span> from the original activation vector, substituting a randomly chosen point at the same distance changes the next token prediction probabilities significantly less than substituting the SAE reconstruction[1] (measured by both KL and loss). This is true for all layers of the model (~2x to ~4.5x increase in KL and loss over baseline) and is not

en-gb

0:33

“How to safely use an optimizer” by Simon Fischer

LessWrong (30+ Karma) ·

2024/03/29

This article contains more than 100 uses of logical or mathematical notation, so an audio narration would be too hard to follow. You'll find a link to the original text in the episode description. ---First published: March 28th, 2024 Source: https://www.lesswrong.com/posts/A9Xvme7bDaZJtYm4m/how-to-safely-use-an-optimizer --- Narrated by TYPE III AUDIO.

en-gb

5:23

[Linkpost] “Practically-A-Book Review: Rootclaim...

LessWrong (30+ Karma) ·

2024/03/28

This is a linkpost for https://www.astralcodexten.com/p/practically-a-book-review-rootclaimLots of people already know about ACX/SSC, but I think that crossposting to LW is unusually valuable in this particular case, since lots of people were waiting for a big schelling-point overview of the 15-hour Rootclaim Lab Leak debate, and unlike LW, ACX's comment section is a massive vote-less swamp that lags the entire page.Here are the first 10 paragraphs:Saar Wilf is an ex-Israeli entrepreneur. Since

en-gb

13:47

“Was Releasing Claude-3 Net-Negative?” by Logan Riggs

LessWrong (30+ Karma) ·

2024/03/28

There's been a lot of discussion among safety-concerned people about whether it was bad for Anthropic to release Claude-3. I felt like I didn’t have a great picture of all the considerations here, and I felt that people were conflating many different types of arguments for why it might be bad. So I decided to try to write down an at-least-slightly-self-contained description of my overall views and reasoning here. Tabooing “Race Dynamics”I’ve heard a lot of people say that this “is bad for race

en-gb

9:02

[Linkpost] “Come to Manifest 2024 (June 7-9 in...

LessWrong (30+ Karma) ·

2024/03/28

This is a linkpost for https://news.manifold.markets/p/come-to-manifest-2024-june-7-9-in TLDR Manifold is hosting a festival for prediction markets: Manifest 2024! We’ll have serious talks, attendee-run workshops, and fun side events over the weekend. Chat with special guests like Nate Silver, Scott Alexander, Robin Hanson, Dwarkesh Patel, Cate Hall, and more at this second in-person gathering of the forecasting & prediction market community! Tickets & more info: manifest.is WHEN: June 7-9,

en-gb

71:31

[Linkpost] “The Cognitive-Theoretic Model of the...

LessWrong (30+ Karma) ·

2024/03/27

This is a linkpost for https://unstablerontology.substack.com/p/the-cognitive-theoretic-model-ofAbout 15 years ago, I read Malcolm Gladwell's Outliers. He profiled Chris Langan, an extremely high-IQ person, claiming that he had only mediocre accomplishments despite his high IQ. Chris Langan's theory of everything, the Cognitive Theoretic Model of the Universe, was mentioned. I considered that it might be worth checking out someday. Well, someday has happened, and I looked into CTMU, prompted by Alex

en-gb

0:37

[Linkpost] “Daniel Kahneman has died” by DanielFilan

LessWrong (30+ Karma) ·

2024/03/27

This is a linkpost for https://www.washingtonpost.com/obituaries/2024/03/27/daniel-kahneman-dead/He was 90 years old. His death was confirmed by his stepdaughter Deborah Treisman, the fiction editor for the New Yorker. She did not say where or how he died. --- First published: March 27th, 2024 Source: https://www.lesswrong.com/posts/xWoaT3wLRQx8Rf4AX/daniel-kahneman-has-died Linkpost

en-gb

1:55

[Linkpost] “Nick Bostrom’s new book, ‘Deep Utopia’,...

LessWrong (30+ Karma) ·

2024/03/27

This is a linkpost for https://nickbostrom.com/deep-utopia/ Description: A greyhound catching the mechanical lure—what would he actually do with it? Has he given this any thought? Bostrom's previous book, Superintelligence: Paths, Dangers, Strategies changed the global conversation on AI and became a New York Times bestseller. It focused on what might happen if AI development goes wrong. But what if things go right? Suppose that we develop superintelligence safely, govern it well, and make good use

en-gb

5:58

“AE Studio @ SXSW: We need more AI consciousness...

LessWrong (30+ Karma) ·

2024/03/27

Quick update from AE Studio: last week, Judd (AE's CEO) hosted a panel at SXSW with Anil Seth, Allison Duettmann, and Michael Graziano, entitled “The Path to Conscious AI” (discussion summary here[1]). We’re also making available an unedited Otter transcript/recording for those who might want to read along or increase the speed of the playback. Why AI consciousness research seems critical to usWith the release of each new frontier model seems to follow a cascade of questions probing whether or not

en-gb

14:45

“Failures in Kindness” by silentbob

LessWrong (30+ Karma) ·

2024/03/26

There's a particular kind of widespread human behavior that is kind on the surface, but upon closer inspection reveals quite the opposite. This post is about four such patterns. Computational KindnessOne of the most useful ideas I got out of Algorithms to Live By is that of computational kindness. I was quite surprised to only find a single mention of the term on lesswrong. So now there's two.Computational kindness is the antidote to a common situation: imagine a friend from a different country is

en-gb

5:12

“Modern Transformers are AGI, and Human-Level” by...

LessWrong (30+ Karma) ·

2024/03/26

This is my personal opinion, and in particular, does not represent anything like a MIRI consensus; I've gotten push-back from almost everyone I've spoken with about this, although in most cases I believe I eventually convinced them of the narrow terminological point I'm making.In the AI x-risk community, I think there is a tendency to ask people to estimate "time to AGI" when what is meant is really something more like "time to doom" (or, better, point-of-no-return). For about a year, I've been

en-gb

12:18

“My Interview With Cade Metz on His Reporting About...

LessWrong (30+ Karma) ·

2024/03/26

On 16 March 2024, I sat down to chat with New York Times technology reporter Cade Metz! In part of our conversation, transcribed below, we discussed his February 2021 article "Silicon Valley's Safe Space", covering Scott Alexander's Slate Star Codex blog and the surrounding community. The transcript has been significantly edited for clarity. (It turns out that real-time conversation transcribed completely verbatim is full of filler words, false starts, crosstalk, "uh huh"s, "yeah"s, pauses while one

en-gb

16:50

“Announcing Neuronpedia: Platform for accelerating...

LessWrong (30+ Karma) ·

2024/03/26

This posts assumes basic familiarity with Sparse Autoencoders. For those unfamiliar with this technique, we highly recommend the introductory sections of these papers. TL;DRNeuronpedia is a platform for mechanistic interpretability research. It was previously focused on crowdsourcing explanations of neurons, but we’ve pivoted to accelerating researchers for Sparse Autoencoders (SAEs) by hosting models, feature dashboards, data visualizations, tooling, and more. Important Links Explore: The SAE

en-gb

49:27

“Should rationalists be spiritual / Spirituality as...

LessWrong (30+ Karma) ·

2024/03/26

Kaj_SotalaI just started thinking about what I would write to someone who disagreed with me on the claim "Rationalists would be better off if they were more spiritual/religious", and for this I'd need to define what I mean by "spiritual". Here are some things that I would classify under "spirituality": Rationalist Solstices (based on what I've read about them, not actually having been in one)Meditation, especially the kind that shows you new things about the way your mind worksSome forms of therapy,

en-gb

44:35

“On attunement” by Joe Carlsmith

LessWrong (30+ Karma) ·

2024/03/25

(Cross-posted from my website. Podcast version here, or search for "Joe Carlsmith Audio" on your podcast app. This essay is part of a series that I'm calling "Otherness and control in the age of AGI." I'm hoping that the individual essays can be read fairly well on their own, but see here for brief summaries of the essays that have been released thus far.) "You, moon, You, Aleksander, fire of cedar logs. Waters close over us, a name lasts but an instant. Not important whether the generations hold

en-gb

17:32

“My Detailed Notes & Commentary from Secular...

LessWrong (30+ Karma) ·

2024/03/25

Previously: General Thoughts on Secular Solstice.This blog post is my scattered notes and ramblings about the individual components (talks and songs) of Secular Solstice in Berkeley. Talks have their title in bold, and I split the post into two columns, with the notes I took about the content of the talk on the left and my comments on the talk on the right. Songs have normal formatting. Bonfire The CircleThis feels like a sort of whig history: a history that neglects most of the complexities and

en-gb

20:58

“On Lex Fridman’s Second Podcast with Altman” by Zvi

LessWrong (30+ Karma) ·

2024/03/25

Last week Sam Altman spent two hours with Lex Fridman (transcript). Given how important it is to understand where Altman's head is at and learn what he knows, this seemed like another clear case where extensive notes were in order. Lex Fridman overperformed, asking harder questions than I expected and going deeper than I expected, and succeeded in getting Altman to give a lot of what I believe were genuine answers. The task is ‘get the best interviews you can while still getting

en-gb

5:20

“Do not delete your misaligned AGI.” by mako yass

LessWrong (30+ Karma) ·

2024/03/25

In short: Just keeping all copies of potentially strong agents in long-term storage is a trivial way to maintain incentives to cooperate for some classes of misaligned AGI, by allowing us to reward the AGI's cooperation to whatever degree we later calculate had been warranted. In contrast, a policy of deleting misaligned AGI fences them into a corner where, even at great risk of being exposed, they have a greater incentive to attempt deception and escape.I'd guess that most AGI researchers already

en-gb

14:15

“All About Concave and Convex Agents” by mako yass

LessWrong (30+ Karma) ·

2024/03/25

An entry-level characterization of some types of guy in decision theory, and in real life, interspersed with short stories about themA concave function bends down. A convex function bends up. A linear function does neither.A utility function is just a function that says how good different outcomes are. They describe an agent's preferences. Different agents have different utility functions.Usually, a utility function assigns scores to outcomes or histories, but in article we'll define a sort of

en-gb

4,491 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Reflections

Livewire Labs

ForGeeks

ForGeeks

FOX on Tech

FOX News Podcasts

The Linux Cast

The Linux Cast