PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

4:15

“Twitter thread on AI safety evals” by Richard_Ngo

LessWrong (30+ Karma) ·

2024/07/31

This is a link post.Epistemic status: raising concerns, rather than stating confident conclusions.I’m worried that a lot of work on AI safety evals matches the pattern of “Something must be done. This is something. Therefore this must be done.” Or, to put it another way: I judge eval ideas on 4 criteria, and I often see proposals which fail all 4. The criteria:1. Possible to measure with scientific rigor.Some things can be easily studied in a lab; others are entangled with a lot of real-world

en-gb

23:25

“RTFB: California’s AB 3211” by Zvi

LessWrong (30+ Karma) ·

2024/07/30

Some in the tech industry decided now was the time to raise alarm about AB 3211. As Dean Ball points out, there's a lot of bills out there. One must do triage. Dean Ball: But SB 1047 is far from the only AI bill worth discussing. It's not even the only one of the dozens of AI bills in California worth discussing. Let's talk about AB 3211, the California Provenance, Authenticity, and Watermarking Standards Act, written by Assemblymember Buffy Wicks, who represents the East Bay. SB 1047 is

en-gb

23:22

“Self-Other Overlap: A Neglected Approach to AI...

LessWrong (30+ Karma) ·

2024/07/30

Figure 1. Image generated by DALL-3 to represent the concept of self-other overlapMany thanks to Bogdan Ionut-Cirstea, Steve Byrnes, Gunnar Zarnacke, Jack Foxabbott and Seong Hah Cho for critical comments and feedback on earlier and ongoing versions of this work.SummaryIn this post, we introduce self-other overlap training: optimizing for similar internal representations when the model reasons about itself and others while preserving performance. There is a large body of evidence suggesting that

en-gb

13:10

“Understanding Positional Features in Layer 0 SAEs”...

LessWrong (30+ Karma) ·

2024/07/30

This is an informal research note. It is the result of a few-day exploration into positional SAE features conducted as part of Neel Nanda's training phase of the ML Alignment & Theory Scholars Program - Summer 2024 cohort.Thanks to Andy Arditi, Arthur Conmy and Stefan Heimersheim for helpful feedback. Thanks to Joseph Bloom for training this SAE. SummaryFigure 1:(Dots)The top 3 PCA components of rows 1 to 127 of gpt2-small's positional embedding matrix explain 95% of their variance

en-gb

16:02

“This is already your second chance” by Malmesbury

LessWrong (30+ Karma) ·

2024/07/28

Cross-posted from Substack. 1.And the sky opened, and from the celestial firmament descended a cube of ivory the size of a skyscraper, lifted by ten thousand cherubim and seraphim. And the cube slowly landed among the children of men, crushing the frail metal beams of the Golden Gate Bridge under its supernatural weight. On its surface were inscribed the secret instructions that would allow humanity to escape the imminent AI apocalypse. And these instructions were… On July 30th, 2024: print a

en-gb

12:28

“Unlocking Solutions” by James Stephen Brown

LessWrong (30+ Karma) ·

2024/07/28

This is a link post. Understanding Coordination ProblemsThe following is a post introducing coordination problems, using the examples of poaching, civilisational development, drug addiction and affirmative action. It draws on my experience as a documentary filmmaker. The post is available for free in its original format at nonzerosum.games.When I was eleven, I disassembled the lock to our back door, and as I opened the housing… it exploded, scattering six tiny brass pellets on to the floor.I

en-gb

16:51

“Re: Anthropic’s suggested SB-1047 amendments” by...

LessWrong (30+ Karma) ·

2024/07/27

This is a link post.If you're familiar with SB 1047, I recommend reading the letter in full; it's only 7 pages.I'll go through their list of suggested changes and briefly analyze them, and then make a couple high-level points. (I am not a lawyer and nothing written here is legal advice.) Major ChangesGreatly narrow the scope of pre-harm enforcement to focus solely on (a) failure to develop, publish, or implement an SSP[1] (the content of which is up to the company); (b) companies making materially

en-gb

2:50

“Safety consultations for AI lab employees” by Zach...

LessWrong (30+ Karma) ·

2024/07/27

Many people who are concerned about AI x-risk work at AI labs, in the hope of doing directly useful work, boosting a relatively responsible lab, or causing their lab to be safer on the margin.Labs do lots of stuff that affects AI safety one way or another. It would be hard enough to follow all this at best; in practice, labs are incentivized to be misleading in both their public and internal comms, making it even harder to follow what's happening. And so people end up misinformed about what's

en-gb

6:20

“Inspired by: Failures in Kindness” by X4vier

LessWrong (30+ Karma) ·

2024/07/27

silentbob's post "Failures in Kindness" is excellent. I love the idea that sometimes, when we exaimine a situation in depth, the most "kind" course of action can be highly conterintuitive. A few other examples I'd like to offer: Appreciative KindnessImagine you meet a friend-of-a-friend for the first time while attending a gathering at their home. "Hey, welcome! It's great to meet you - can I get you anything?" they ask. There's nothing you really want right now, and you don't want to take from

en-gb

13:40

“End Single Family Zoning by Overturning Euclid V...

LessWrong (30+ Karma) ·

2024/07/27

This is a link post.On 75 percent or more of the residential land in most major American cities it is illegal to build anything other than a detached single-family home. 95.8 percent of total residential land area in California is zoned as single-family-only, which is 30 percent of all land in the state. Restrictive zoning regulations such as these probably lower GDP per capita in the US by 8-36%. That's potentially tens of thousands of dollars per person.Map of land use in San Jose, California

en-gb

3:30

“How the AI safety technical landscape has changed in...

LessWrong (30+ Karma) ·

2024/07/26

I asked the Constellation Slack channel how the technical AIS landscape has changed since I last spent substantial time in the Bay Area (September 2023), and I figured it would be useful to post this (with the permission of the contributors to either post with or without attribution). Curious if commenters agree or would propose additional changes!This conversation has been lightly edited to preserve anonymity.Me: One reason I wanted to spend a few weeks in Constellation was to sort of

en-gb

2:43

“Index of rationalist groups in the Bay July 2024” by...

LessWrong (30+ Karma) ·

2024/07/26

The Bay Area rationalist community has an entry problem! Lots of listed groups are dead, the last centralized index disappeared, communication moved to private discord and slacks. This is bad, so we're making a new index, hopefully up to date and as complete as we can! CommunicationDiscord: Bay Area Rationalists: https://discord.gg/EpG4xUVKtfEmail Group: BayAreaLessWrong: https://groups.google.com/g/bayarealesswrong Local Meetup GroupsTaco Tuesday: by Austin Chen, founder emeritus of Manifold. Check

en-gb

4:43

“Pacing Outside the Box: RNNs Learn to Plan in...

LessWrong (30+ Karma) ·

2024/07/26

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.Work done at FAR AI.There has been a lot of conceptual work on mesa-optimizers: neural networks that develop internal goals that may differ from their training objectives (the inner alignment problem). There is an abundance of good ideas for empirical work (find search in a NN, interpret it), but very little actual execution, partly because we did not have a clear-cut example of a mesa-optimizer

en-gb

15:55

“Universal Basic Income and Poverty” by Eliezer...

LessWrong (30+ Karma) ·

2024/07/26

(Crossposted from Twitter)I'm skeptical that Universal Basic Income can get rid of grinding poverty, since somehow humanity's 100-fold productivity increase (since the days of agriculture) didn't eliminate poverty.Some of my friends reply, "What do you mean, poverty is still around? 'Poor' people today, in Western countries, have a lot to legitimately be miserable about, don't get me wrong; but they also have amounts of clothing and fabric that only rich merchants could afford a thousand years ago;

en-gb

15:55

“Universal Basic Income and Poverty” by Eliezer...

LessWrong (30+ Karma) ·

2024/07/26

en-gb

0:37

“A Solomonoff Inductor Walks Into a Bar: Schelling...

LessWrong (30+ Karma) ·

2024/07/26

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: July 26th, 2024 Source: https://www.lesswrong.com/posts/QA7bQHpKymPBFBuHb/a-solomonoff-inductor-walks-into-a-bar-schelling-points-for --- Narrated by TYPE III AUDIO.

en-gb

4:00

“‘AI achieves silver-medal standard solving...

LessWrong (30+ Karma) ·

2024/07/25

This is a link post.Google DeepMind reports on a system for solving mathematical problems that allegedly is able to give complete solutions to four of the six problems on the 2024 IMO, putting it near the top of the silver-medal category.Well, actually, two systems for solving mathematical problems: AlphaProof, which is more general-purpose, and AlphaGeometry, which is specifically for geometry problems. (This is AlphaGeometry 2; they reported earlier this year on a previous version of

en-gb

3:39

“‘AI achieves silver-medal standard solving...

LessWrong (30+ Karma) ·

2024/07/25

en-gb

31:26

“A framework for thinking about AI power-seeking” by...

LessWrong (30+ Karma) ·

2024/07/25

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This post lays out a framework I’m currently using for thinking about when AI systems will seek power in problematic ways. I think this framework adds useful structure to the too-often-left-amorphous “instrumental convergence thesis,” and that it helps us recast the classic argument for existential risk from misaligned AI in a revealing way. In particular, I suggest, this recasting highlights how much classic

en-gb

59:06

“Llama Llama-3-405B?” by Zvi

LessWrong (30+ Karma) ·

2024/07/25

It's here. The horse has left the barn. Llama-3.1-405B, and also Llama-3.1-70B and Llama-3.1-8B, have been released, and are now open weights. Early indications are that these are very good models. They were likely the best open weight models of their respective sizes at time of release. Zuckerberg claims that open weights models are now competitive with closed models. Yann LeCun says ‘performance is on par with the best closed models.’ This is closer to true than in the past, and as corporate

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