PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

57:56

“The Plan - 2023 Version” by johnswentworth

LessWrong (30+ Karma) ·

2023/12/29

Background: The Plan, The Plan: 2022 Update. If you haven’t read those, don’t worry, we’re going to go through things from the top this year, and with moderately more detail than before. 1. What's Your Plan For AI Alignment?Median happy trajectory: Sort out our fundamental confusions about agency and abstraction enough to do interpretability that works and generalizes robustly.Look through our AI's internal concepts for a good alignment target, thenRetarget the Search[1].…Profit!We’ll talk about

en-gb

12:10

[Linkpost] “Dark Skies Book Review” by PeterMcCluskey

LessWrong (30+ Karma) ·

2023/12/29

This is a linkpost for https://bayesianinvestor.com/blog/index.php/2023/12/28/dark-skies/Book review: Dark Skies: Space Expansionism, Planetary Geopolitics, and the Ends of Humanity, by Daniel Deudney. Dark Skies is an unusually good and bad book. Good in the sense that 95% of the book consists of uncontroversial, scholarly, mundane claims that accurately describe the views that Deudney is attacking. These parts of the book are careful to distinguish between value differences and claims about

en-gb

79:26

“AI #44: Copyright Confrontation” by Zvi

LessWrong (30+ Karma) ·

2023/12/29

The New York Times has thrown down the gauntlet, suing OpenAI and Microsoft for copyright infringement. Others are complaining about recreated images in the otherwise deeply awesome MidJourney v6.0. As is usually the case, the critics misunderstand the technology involved, complain about infringements that inflict no substantial damages, engineer many of the complaints being made and make cringeworthy accusations. That does not, however, mean that The New York Times case is baseless. There are

en-gb

19:40

“Will 2024 be very hot? Should we be worried?” by A.H.

LessWrong (30+ Karma) ·

2023/12/29

tl;dr: There are several trends which suggest that global temperatures over the next year will experience a short-term increase, relative to the long-term increase in temperatures caused by man-made global warming. Credits: Most of the information comes from Berkley Earth monthly temperature updates. Several people on Twitter (Robert Rohde, Zeke Hausfather, James Hansen and Roko) have also been talking about the issues discussed here for a while.Man-made global warming has been causing a steady,

en-gb

38:14

“E.T. Jaynes Probability Theory: The logic of Science...

LessWrong (30+ Karma) ·

2023/12/28

This book (available as a free pdf here) is one of the foundational texts for Rationalists; Eliezer refers to Jaynes as The Level Above Mine. While we agree that Jaynes is very lucid and the book is wonderful, we also think the book's target audience are graduate physics students. It occupies a sparse area of the literature, between statistics, math, causality, and philosophy of science that contains real, practical lessons about how to think about the world and its uncertainty. Here, we will try to

en-gb

30:26

“Natural Latents: The Math” by johnswentworth, David...

LessWrong (30+ Karma) ·

2023/12/27

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.Natural latents are a relatively elegant piece of math which we figured out over the past year, in our efforts to boil down and generalize various results and examples involving natural abstraction. In particular, this new framework handles approximation well, which was a major piece missing previously. This post will present the math of natural latents, with a handful of examples but otherwise minimal commentary

en-gb

2:21

“NYT is suing OpenAI&Microsoft for alleged copyright...

LessWrong (30+ Karma) ·

2023/12/27

Unpaywalled article, the lawsuit.(I don't have a law degree, this is not legal advice, my background is going through a US copyright law course many years ago.) I've read most of the lawsuit and skimmed through the rest, some quick thoughts on the allegations: Memorisation: when ChatGPT outputs text that closely copies original NYT content, this is clearly a copyright infringement. I think it's clear that OpenAI & Microsoft should be paying everyone whose work their LLMs reproduce.Training: it's

en-gb

12:02

[Linkpost] “In Defense of Epistemic Empathy” by Kevin...

LessWrong (30+ Karma) ·

2023/12/27

This is a linkpost for https://kevindorst.substack.com/p/in-defense-of-epistemic-empathyTLDR: Why think your ideological opponents are unreasonable? Common reasons: their views are (1) absurd, or (2) refutable, or (3) baseless, or (4) conformist, or (5) irrational. None are convincing.Elizabeth is skeptical about the results of the 2020 election. Theo thinks Republicans are planning to institute a theocracy. Alan is convinced that AI will soon take over the world.You probably think some (or all) of

en-gb

28:12

“Critical review of Christiano’s disagreements with...

LessWrong (30+ Karma) ·

2023/12/27

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a review of Paul Christiano's article "where I agree and disagree with Eliezer". Written for the LessWrong 2022 Review.In the existential AI safety community, there is an ongoing debate between positions situated differently on some axis which doesn't have a common agreed-upon name, but where Christiano and Yudkowsky can be regarded as representatives of the two directions[1]. For the sake of this review, I

en-gb

8:22

“AGI will be made of heterogeneous components,...

LessWrong (30+ Karma) ·

2023/12/27

This post is prompted by two recent pieces:First, in the podcast "Emergency Pod: Mamba, Memory, and the SSM Moment", Nathan Labenz described how he sees that we are entering the era of heterogeneity in AI architectures because currently we have not just one fundamental block that works very well (the Transformer block), but two kinds of blocks: the Selective SSM (Mamba) block has joined the party. These are natural opposites on the tradeoff scale between episodic cognitive capacity (Transformer's

en-gb

1:58

“METR is hiring!” by Beth Barnes

LessWrong (30+ Karma) ·

2023/12/26

This is a quick update that METR (formerly ARC Evals) is recruiting for four positions. I encourage you to err on the side of applying to positions that interest you even if you’re unsure about your fit! We’re able to sponsor US visas for all the roles below except Research Assistant, and all applications are rolling with no set closing date. Engineering Lead andSenior Software Engineer. You’ll work on our internal platform for evaluating model capabilities (think: 100 docker containers running

en-gb

2:23

“Environmental allergies are curable? (Sublingual...

LessWrong (30+ Karma) ·

2023/12/26

I used to have severe environmental allergies to cats, dogs, and the outdoors. As I kid, I woke up crying most mornings because of my allergies, and I would occasionally wake up with croup and difficulty breathing. I even had to be taken the hospital once.Anyways, I cried enough that my mother found and enrolled me in a study for an experimental treatment called sublingual immunotherapy (SLIT). For the next two years I took under-the-tongue drops, and I presume the drops were formulated with small

en-gb

3:10

[Linkpost] “How ‘Pause AI’ advocacy could be net...

LessWrong (30+ Karma) ·

2023/12/26

This is a linkpost for https://carado.moe/pause-ai-advocacy-could-be-net-harm.htmlIn the olden days, Yudkowsky and Bostrom warned people about the risks associated with developing powerful AI. Many people listened and went "woah, AI is dangerous, we better not build it". A few people went "woah, AI is powerful, I better be the one to build it". And we've got the AI race we have today, where a few organizations (bootstrapped with EA funding) are functionally trying to kill literally everyone, but at

en-gb

1:55

“Flagging Potentially Unfair Parenting” by jefftk

LessWrong (30+ Karma) ·

2023/12/26

Recently I made a post in our kids group about something Lily (9y) had done that was funny, mischievous, and also potentially embarrassing. A friend asked whether Lily knew I was writing about her antics and said they would have felt mortified and a bit betrayed if this had happened to them at this age. I think it was really good they asked! While Lily knows I post this sort of thing in the group, and this time already knew I'd posted this one (and thought it was funny), the friend didn't

en-gb

11:30

“How Emergency Medicine Solves the Alignment Problem”...

LessWrong (30+ Karma) ·

2023/12/26

Emergency medical technicians (EMTs) are not licensed to practice medicine. An EMT license instead grants the authority to perform a specific set of interventions, in specific situations, on behalf of a medical director. The field of emergency medical services (EMS) faces many principal-agent problems that are analogous to the principal-agent problem of designing an intelligent system to act autonomously on your behalf. And many of the solutions EMS uses can be adapted for AI alignment. Separate

en-gb

21:57

“A Crisper Explanation of Simulacrum Levels” by Thane...

LessWrong (30+ Karma) ·

2023/12/23

I've read the previous work on Simulacrum Levels, and I've seen people express some confusion regarding how they work. I'd had some of those confusions myself when I first encountered the concept, and I think they were caused by insufficiently crisp definitions. The extant explanations didn't seem like they offered a proper bottom-up/fundamentals-first mechanism for how simulacrum levels come to exist. Why do they have the specific features and quirks that they have, and not any others? Why is the

en-gb

5:33

“AI’s impact on biology research: Part I, today” by...

LessWrong (30+ Karma) ·

2023/12/23

I'm a biology PhD, and have been working in tech for a number of years. I want to show why I believe that biological research is the most near term, high value application of machine learning. This has profound implications for human health, industrial development, and the fate of the world. In this article I explain the current discoveries that machine learning has enabled in biology. In the next article I will consider what this implies will happen in the near term without major improvements in

en-gb

3:50

[Linkpost] “AI Girlfriends Won’t Matter Much” by...

LessWrong (30+ Karma) ·

2023/12/23

This is a linkpost for https://maximumprogress.substack.com/p/ai-girlfriendsLove and sex are pretty fundamental human motivations, so it's not surprising that they are incorporated into our vision of future technology, including AI.The release of Digi last week immanentized this vision more than ever before. The app combines a sycophant and flirtatious chat feed with an animated character “that eliminates the uncanny valley, while also feeling real, human, and sexy.” Their marketing material

en-gb

41:17

“Fact Finding: Attempting to Reverse-Engineer Factual...

LessWrong (30+ Karma) ·

2023/12/23

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a write up of the Google DeepMind mechanistic interpretability team's investigation of how language models represent facts. This is a sequence of 5 posts, we recommend prioritising reading post 1, and thinking of it as the “main body” of our paper, and posts 2 to 5 as a series of appendices to be skimmed or dipped into in any order. Executive Summary Reverse-engineering circuits with superposition is a

en-gb

7:37

“Measurement tampering detection as a special case of...

LessWrong (30+ Karma) ·

2023/12/23

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.Burns et al at OpenAI released a paper studying various techniques for fine-tuning strong models on downstream tasks using labels produced by weak models. They call this problem “weak-to-strong generalization”, abbreviated W2SG.Earlier this year, we published a paper, Benchmarks for Detecting Measurement Tampering, in which we investigated techniques for the problem of measurement tampering detection (MTD). MTD is

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