PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

63:01

“OpenAI #8: The Right to Warn” by Zvi

LessWrong (30+ Karma) ·

2024/06/17

The fun at OpenAI continues. We finally have the details of how Leopold Aschenbrenner was fired, at least according to Leopold. We have a letter calling for a way for employees to do something if frontier AI labs are endangering safety. And we have continued details and fallout from the issues with non-disparagement agreements and NDAs. Hopefully we can stop meeting like this for a while. Due to jury duty and it being largely distinct, this post does not cover the appointment of General

en-gb

41:53

“Towards a Less Bullshit Model of Semantics” by...

LessWrong (30+ Karma) ·

2024/06/17

Or: Towards Bayesian Natural Language Semantics In Terms Of Interoperable Mental ContentOr: Towards a Theory of Interoperable SemanticsYou know how natural language “semantics” as studied in e.g. linguistics is kinda bullshit? Like, there's some fine math there, it just ignores most of the thing which people intuitively mean by “semantics”.When I think about what natural language “semantics” means, intuitively, the core picture in my head is: I hear/read some words, and my brain translates those

en-gb

0:39

“Degeneracies are sticky for SGD” by Guillaume...

LessWrong (30+ Karma) ·

2024/06/17

This article contains more than fifty 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: June 16th, 2024 Source: https://www.lesswrong.com/posts/JDrxA3vwZAKZfmShz/degeneracies-are-sticky-for-sgd --- Narrated by TYPE III AUDIO.

en-gb

7:20

“(Appetitive, Consummatory) ≈ (RL, reflex)” by Steven...

LessWrong (30+ Karma) ·

2024/06/17

“Appetitive” and “Consummatory” are terms used in the animal behavior literature. I was was briefly confused when I first came across these terms (a year or two ago), because I’m most comfortable thinking in terms of brain algorithms, whereas these terms were about categories of behavior, and the papers I was reading didn’t spell out how the one is related to the other.I’m somewhat embarrassed to write this because the thesis seems so extremely obvious to me now, and it's probably obvious to many

en-gb

18:12

“CIV: a story” by Richard_Ngo

LessWrong (30+ Karma) ·

2024/06/16

This is a link post.The room was cozy despite its size, with wood-lined walls reflecting the dim lighting. At one end, a stone fireplace housed a roaring fire; in the middle stood a huge oak table. The woman seated at the head of it rapped her gavel. “I hereby call to order the first meeting of the Parliamentary Subcommittee on Intergalactic Colonization. We’ll start with brief opening statements, for which each representative will be allocated one minute, including—”“Oh, enough with the pomp,

en-gb

5:15

“MIRI’s June 2024 Newsletter” by Harlan

LessWrong (30+ Karma) ·

2024/06/15

This is a link post. MIRI updates MIRI Communications Manager Gretta Duleba explainsMIRI's current communications strategy. We hope to clearly communicate to policymakers and the general public why there's an urgent need to shut down frontier AI development, and make the case for installing an “off-switch”. This will not be easy, and there is a lot of work to be done. Some projects we’re currently exploring include a new website, a book, and an online reference resource. Rob Bensingerargues, contra

en-gb

19:11

“Fine-tuning is not sufficient for capability...

LessWrong (30+ Karma) ·

2024/06/15

Produced as part of the ML Alignment & Theory Scholars Program - Winter 2023-24 Cohort under the supervision of Evan Hubinger.Acknowledgements: Thanks to Kyle Brady for his many contributions to this project.Abstract. This post argues that the performance elicited by fine-tuning an LLM on a task using a given prompt format does not usefully bound the level of performance observed when the same information is presented in a different structure. Thus, fine-tuned performance provides very little

en-gb

19:23

“Rational Animations’ intro to mechanistic...

LessWrong (30+ Karma) ·

2024/06/15

This is a link post.In our new video, we talk about research on interpreting InceptionV1, a convolutional neural network. Researchers have been able to understand the function of neurons and channels inside the network and uncover visual processing algorithms by looking at the weights. The work on InceptionV1 is early but landmark mechanistic interpretability research, and it functions well as an introduction to the field. We also go into the rationale and goals of the field and mention some more

en-gb

27:03

“Shard Theory - is it true for humans?” by Rishika

LessWrong (30+ Karma) ·

2024/06/14

And is it a good model for value learning in AI? TLDRShard theory proposes a view of value formation where experiences lead to the creation of context-based ‘shards’ that determine behaviour. Here, we go over psychological and neuroscientific views of learning, and find that while shard theory's emphasis on context bears similarity to types of learning such as conditioning, it does not address top-down influences that may decrease the locality of value-learning in the brain. What's Shard Theory

en-gb

105:30

“The Leopold Model: Analysis and Reactions” by Zvi

LessWrong (30+ Karma) ·

2024/06/14

Previously: On the Podcast, Quotes from the PaperThis is a post in three parts. The first part is my attempt to condense Leopold Aschenbrenner's paper and model into its load bearing elements and core logic and dependencies. Two versions here, a long version that attempts to compress with minimal loss, and a short version that gives the gist. The second part goes over where I agree and disagree, and briefly explains why. The third part is the summary of other people's reactions and

en-gb

91:21

“AI #68: Remarkably Reasonable Reactions” by Zvi

LessWrong (30+ Karma) ·

2024/06/14

The big news this week was Apple Intelligence being integrated deeply into all their products. Beyond that, we had a modestly better than expected debate over the new version of SB 1047, and the usual tons of stuff in the background. I got to pay down some writing debt. The bad news is, oh no, I have been called for Jury Duty. The first day or two I can catch up on podcasts or pure reading, but after that it will start to hurt. Wish me luck. Table of Contents AiPhone covers the

en-gb

1:17

“OpenAI appoints Retired U.S. Army General Paul M....

LessWrong (30+ Karma) ·

2024/06/14

This is a link post.Today, Retired U.S. Army General Paul M. Nakasone has joined our Board of Directors. A leading expert in cybersecurity, Nakasone's appointment reflects OpenAI's commitment to safety and security, and underscores the growing significance of cybersecurity as the impact of AI technology continues to grow.As a first priority, Nakasone will join the Board's Safety and Security Committee, which is responsible for making recommendations to the full Board on critical safety and security

en-gb

8:48

“Safety isn’t safety without a social model (or:...

LessWrong (30+ Karma) ·

2024/06/14

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.As an AI researcher who wants to do technical work that helps humanity, there is a strong drive to find a research area that is definitely helpful somehow, so that you don’t have to worry about how your work will be applied, and thus you don’t have to worry about things like corporate ethics or geopolitics to make sure your work benefits humanity.Unfortunately, no such field exists. In particular, technical AI

en-gb

5:01

“‘Full Automation’ is a Slippery Metric” by ozziegooen

LessWrong (30+ Karma) ·

2024/06/13

Research Status: Written & researched quickly. I think the key point is fairly simple and obvious. I relied on Claude to help with rewriting. There's been a growing interest in predicting when various products or jobs will be "fully automated." Will we soon have popular movies, books, or even CEOs that are entirely AI-generated? Some very quickly-found links: - https://manifold.markets/ChaseStevens/will-an-aigenerated-paper-be-accept -

en-gb

8:03

“microwave drilling is impractical” by bhauth

LessWrong (30+ Karma) ·

2024/06/13

This is a link post. microwave drilling startupsI've seen a bunch of articles about startups trying to do microwave drilling of rock for geothermal energy. Multiple people have asked me about Quaise Energy. (Here's a popular video.) I'm tired of hearing about them, so I'm writing this post to explain some of the reasons why their idea is impractical. vaporized rock condenses When rock is vaporized, that rock vapor doesn't just disappear. What happens to it? The answer is, it would quickly condense

en-gb

27:32

“Long-Term Future Fund: March 2024 Payout...

LessWrong (30+ Karma) ·

2024/06/13

Introduction. This payout report covers the Long-Term Future Fund's grantmaking from May 1 2023 to March 31 2024 (11 months). It follows our previous April 2023 payout report. Total funding recommended: $6,290,550 Total funding paid out:$5,363,105 Number of grants paid out: 141 Acceptance rate(excluding desk rejections): 159/672 = 23.7% Acceptance rate(including desk rejections): 159/825 = 19.3% Report authors:Linchuan Zhang (primary author), Caleb Parikh (fund chair), Oliver Habryka, Lawrence

en-gb

27:00

“AiPhone” by Zvi

LessWrong (30+ Karma) ·

2024/06/13

Apple was for a while rumored to be planning launch for iPhone of AI assisted emails, texts, summaries and so on including via Siri, to be announced at WWDC 24. It's happening. Apple's keynote announced the anticipated partnership with OpenAI. The bottom line is that this is Siri as the AI assistant with full access to everything on your phone, with relatively strong privacy protections. Mostly it is done on device, the rest via ‘private cloud compute.’ The catch is that when they need

en-gb

7:29

“My AI Model Delta Compared To Christiano” by...

LessWrong (30+ Karma) ·

2024/06/12

Preamble: Delta vs CruxThis section is redundant if you already read My AI Model Delta Compared To Yudkowsky.I don’t natively think in terms of cruxes. But there's a similar concept which is more natural for me, which I’ll call a delta.Imagine that you and I each model the world (or some part of it) as implementing some program. Very oversimplified example: if I learn that e.g. it's cloudy today, that means the “weather” variable in my program at a particular time[1] takes on the value “cloudy”

en-gb

7:53

“Anthropic’s Certificate of Incorporation” by Zach...

LessWrong (30+ Karma) ·

2024/06/12

Yesterday I obtained Anthropic's[1] Certificate of Incorporation, and its past versions, from the State of Delaware. I don't recommend reading it.[2] This post is about what the CoI tells us about Anthropic's Long-Term Benefit Trust (context: Maybe Anthropic's Long-Term Benefit Trust is powerless).Tl;dr: the only new information of moderate importance is the voting thresholds necessary to modify Trust stuff. My concerns all still stand in some form. Absence of badness is a small positive

en-gb

1:57

“[New Feature] Your Subscribed Feed” by Ruby

LessWrong (30+ Karma) ·

2024/06/12

tl;drLessWrong now has a Subscribed tab (next to the Latest tab and Enriched tab[1]). You can now "follow" users, which means their posts and comments will show up in your Subscribed tab.You can follow users via multiple methods: Using the widget on the Subscribed tab:2. You can follow people from their user profile:3. You can follow people using the user tooltip that comes up when you hover on their username.<insert image> The full briefA while back...notifiy on all comments. I wanted a

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