PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

17:13

“Intransitive Trust” by Screwtape

LessWrong (30+ Karma) ·

2024/05/27

1."Transitivity" is a property in mathematics and logic. Put simply, if something is transitive it means that there's a relationship between things where when x relates to y, and y relates to z, there's the same relationship between x and z. For a more concrete example, think of size. If my car is bigger than my couch, and my couch is bigger than my hat, you know that my car is bigger than my hat. (I am not a math major, and if there's a consensus in the comments that I'm using the wrong term here

en-gb

4:50

“Book review: Everything Is Predictable” by...

LessWrong (30+ Karma) ·

2024/05/27

This is a link post.Book review: Everything Is Predictable: How Bayesian Statistics Explain Our World, by Tom Chivers. Many have attempted to persuade the world to embrace a Bayesian worldview, but none have succeeded in reaching a broad audience. E.T. Jaynes' book has been a leading example, but its appeal is limited to those who find calculus enjoyable, making it unsuitable for a wider readership. Other attempts to engage a broader audience often focus on a narrower understanding, such as

en-gb

49:57

“I am the Golden Gate Bridge” by Zvi

LessWrong (30+ Karma) ·

2024/05/27

Easily Interpretable Summary of New Interpretability Paper Anthropic has identified (full paper here) how millions of concepts are represented inside Claude Sonnet, their current middleweight model. The features activate across modalities and languages as tokens approach the associated context. This scales up previous findings from smaller models. By looking at neuron clusters, they defined a distance measure between clusters. So the Golden Gate Bridge is close to various San Francisco and

en-gb

5:13

“Maybe Anthropic’s Long-Term Benefit Trust is...

LessWrong (30+ Karma) ·

2024/05/27

Crossposted from AI Lab Watch. Subscribe on Substack.Introduction. Anthropic has an unconventional governance mechanism: an independent "Long-Term Benefit Trust" elects some of its board. Anthropic sometimes emphasizes that the Trust is an experiment, but mostly points to it to argue that Anthropic will be able to promote safety and benefit-sharing over profit.[1]But the Trust's details have not been published and some information Anthropic has shared is concerning. In particular, Anthropic's

en-gb

3:19

“Computational Mechanics Hackathon (June 1 & 2)” by...

LessWrong (30+ Karma) ·

2024/05/27

Join our Computational Mechanics Hackathon, organized with the support of APART, PIBBSS and Simplex. This is an opportunity to learn more about Computational Mechanics, its applications to AI interpretability & safety, and to get your hands dirty by working on a concrete project together with a team and supported by Adam & Paul. Also, there will be cash prizes for the best projects! Read more and sign up for the event here. We’re excited about Computational Mechanics as a framework because

en-gb

65:38

“Review: Conor Moreton’s ‘Civilization &...

LessWrong (30+ Karma) ·

2024/05/26

Author's note: in honor of the upcoming LessOnline event, I'm sharing this one here on LessWrong rather than solely on my substack. If you like it, you should subscribe to my substack, which you can do for free (paid subscribers see stuff a week early). I welcome discussion down below but am not currently committing to participating myself.Dang it, I knew I should have gone with my first instinct, and photocopied the whole book first. But then again, given that it vanished as soon as I got to the

en-gb

16:08

“Notifications Received in 30 Minutes of Class” by...

LessWrong (30+ Karma) ·

2024/05/26

Introduction. If you are choosing to read this post, you've probably seen the image below depicting all the notifications students received on their phones during one class period. You probably saw it as a retweet of this tweet, or in one of Zvi's posts. Did you find this data plausible, or did you roll to disbelieve? Did you know that the image dates back to at least 2019? Does that fact make you more or less worried about the truth on the ground as of 2024?Last month, I performed an enhanced

en-gb

5:29

“Level up your spreadsheeting” by angelinahli

LessWrong (30+ Karma) ·

2024/05/25

This is a link post.Epistemic status: Passion project / domain I’m pretty opinionated about, just for fun.In this post, I walk through some principles I think good spreadsheets abide by, and then in the companion piece, I walk through a whole bunch of tricks I've found valuable.Illustrated by GPT-4o Who am I?I’ve spent a big chunk of my (short) professional career so far getting good at Excel and Google Sheets.[1] As such, I’ve accumulated a bunch of opinions on this topic. Who should read this?This

en-gb

69:54

“The Schumer Report on AI (RTFB)” by Zvi

LessWrong (30+ Karma) ·

2024/05/25

Or at least, Read the Report (RTFR). There is no substitute. This is not strictly a bill, but it is important. The introduction kicks off balancing upside and avoiding downside, utility and risk. This will be a common theme, with a very strong ‘why not both?’ vibe. Early in the 118th Congress, we were brought together by a shared recognition of the profound changes artificial intelligence (AI) could bring to our world: AI's capacity to revolutionize the realms of science, medicine,

en-gb

7:43

“AI companies aren’t really using external...

LessWrong (30+ Karma) ·

2024/05/24

New blog: AI Lab Watch. Subscribe on Substack.Many AI safety folks think that METR is close to the labs, with ongoing relationships that grant it access to models before they are deployed. This is incorrect. METR (then called ARC Evals) did pre-deployment evaluation for GPT-4 and Claude 2 in the first half of 2023, but it seems to have had no special access since then.[1] Other model evaluators also seem to have little access before deployment.Frontier AI labs' pre-deployment risk assessment should

en-gb

4:17

“minutes from a human-alignment meeting” by bhauth

LessWrong (30+ Karma) ·

2024/05/24

"OK, let's get this meeting started. We're all responsible for development of this new advanced intelligence 'John'. We want John to have some kids with our genes, instead of just doing stuff like philosophy or building model trains, and this meeting is to discuss how we can ensure John tries to do that." "It's just a reinforcement learning problem, isn't it? We want kids to happen, so provide positive reinforcement when that happens." "How do we make sure the kids are ours?" "There's a more

en-gb

22:49

“What mistakes has the AI safety movement made?” by...

LessWrong (30+ Karma) ·

2024/05/24

This is the third of three posts summarizing what I learned when I interviewed 17 AI safety experts about their "big picture" of the existential AI risk landscape: how AGI will play out, how things might go wrong, and what the AI safety community should be doing. See here for a list of the participants and the standardized list of questions I asked.This post summarizes the responses I received from asking “Are there any big mistakes the AI safety community has made in the past or are currently

en-gb

2:19

“The case for stopping AI safety research” by catubc

LessWrong (30+ Karma) ·

2024/05/24

TLDR: AI systems are failing in obvious and manageable ways for now. Fixing them will push the failure modes beyond our ability to fix. The AI safety community is also doing a huge economic service to developers. Our belief that our minds can "fix" a super-intelligence - especially bit by bit - needs to be re-thought. I wanted to write this post forever, but now seems like a good time. The case is simple, I hope it takes you 1min to read. AI safety research is equal to AI capabilities research. We

en-gb

28:17

“Talent Needs in Technical AI Safety” by yams, Carson...

LessWrong (30+ Karma) ·

2024/05/24

Co-Authors: @Carson Jones, @McKennaFitzgerald, @Ryan Kidd MATS tracks the evolving landscape of AI safety[1] to ensure that our program continues to meet the talent needs of safety orgs. As the field has grown, it's become increasingly necessary to adopt a more formal approach to this monitoring, since relying on a few individuals to intuitively understand the dynamics of such a vast ecosystem could lead to significant missteps.[2]In the winter and spring of 2024, we conducted 29 interviews, ranging

en-gb

11:28

“Big Picture AI Safety: Introduction” by EuanMcLean

LessWrong (30+ Karma) ·

2024/05/23

tldr: I conducted 17 semi-structured interviews of AI safety experts about their big picture strategic view of the AI safety landscape: how will human-level AI play out, how things might go wrong, and what should the AI safety community be doing. While many respondents held “traditional” views (e.g. the main threat is misaligned AI takeover), there was more opposition to these standard views than I expected, and the field seems more split on many important questions than someone outside the field

en-gb

2:04

“Paper in Science: Managing extreme AI risks amid...

LessWrong (30+ Karma) ·

2024/05/23

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.https://www.science.org/doi/10.1126/science.adn0117Authors:Yoshua Bengio, Geoffrey Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atılım Güneş Baydin, Sheila McIlraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca Dragan, Philip Torr, Stuart Russell, Daniel Kahneman, Jan Brauner*, Sören

en-gb

8:32

“‘Which chains-of-thought was that faster than?’” by...

LessWrong (30+ Karma) ·

2024/05/23

Here's some good advice from Eliezer: TAP: "How could I have thought that faster?" WHEN[1]you complete a chain-of-thoughtTHEN ask yourself, "how could I have thought that faster?"I really like this heuristic, and it's already paid its rent several times over for me. Most recently today, and the (slightly edited) cognitive trace of it serves as a good example: Example: To find the inverse of something, trace the chain forward a few times first I was in the context of having just asked myself "what's

en-gb

6:06

“Higher-Order Forecasts” by ozziegooen

LessWrong (30+ Karma) ·

2024/05/23

Higher-order forecasting could be a useful concept for prediction markets and forecasting systems more broadly. The core idea is straightforward: Nth-order forecasts are forecasts about (N-1)th order forecasts. Abstract representation of 2nd-order forecasts. Dall-E 3 Examples Here are some examples: 0-Order Forecasting (i.e., the ground truth) Biden won the 2020 U.S. presidential election The US GDP in 2023 was $27 trillion 1st-Order Forecasting (i.e., regular forecasting) What is the chance

en-gb

3:35

“Announcing Human-aligned AI Summer School” by...

LessWrong (30+ Karma) ·

2024/05/22

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.The fourth Human-aligned AI Summer School will be held in Prague from 17th to 20th July 2024. We will meet for four intensive days of talks, workshops, and discussions covering latest trends in AI alignment research and broader framings of AI alignment research. Apply now, applications are evaluated on a rolling basis. The intended audience of the school are people interested in learning more

en-gb

30:33

“Do Not Mess With Scarlett Johansson” by Zvi

LessWrong (30+ Karma) ·

2024/05/22

I repeat. Do not mess with Scarlett Johansson. You would think her movies, and her suit against Disney, would make this obvious. Apparently not so. Andrej Karpathy (co-founder OpenAI, departed earlier), May 14: The killer app of LLMs is Scarlett Johansson. You all thought it was math or something. You see, there was this voice they created for GPT-4o, called ‘Sky.’ People noticed it sounded suspiciously like Scarlett Johansson, who voiced the AI in the movie Her, which Sam

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