PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

13:53

“Memorizing weak examples can elicit strong behavior...

LessWrong (30+ Karma) ·

2024/06/07

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.We’ve recently done some research looking into sandbagging: examining when models can succeed at intentionally producing low-quality outputs despite attempts at fine-tuning them to perform well. One reason why sandbagging could be concerning is because scheming models might try to appear less capable than they actually are in capability evaluations, which could result in these models being deployed with

en-gb

1:55

“Scaling and evaluating sparse autoencoders” by leogao

LessWrong (30+ Karma) ·

2024/06/07

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.[Blog] [Paper] [Visualizer]Abstract:Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders need to be very large to recover all relevant features. However, studying the properties of autoencoder scaling is difficult due to the need

en-gb

5:30

“Response to Aschenbrenner’s ‘Situational Awareness’”...

LessWrong (30+ Karma) ·

2024/06/07

(Cross-posted from Twitter.) My take on Leopold Aschenbrenner's new report: I think Leopold gets it right on a bunch of important counts.Three that I especially care about: Full AGI and ASI soon. (I think his arguments for this have a lot of holes, but he gets the basic point that superintelligence looks 5 or 15 years off rather than 50+.)This technology is an overwhelmingly huge deal, and if we play our cards wrong we're all dead.Current developers are indeed fundamentally unserious about the core

en-gb

5:03

“Humming is not a free $100 bill” by Elizabeth

LessWrong (30+ Karma) ·

2024/06/06

Last month I posted about humming as a cheap and convenient way to flood your nose with nitric oxide (NO), a known antiviral. Alas, the economists were right, and the benefits were much smaller than I estimated.The post contained one obvious error and one complication. Both were caught by Thomas Kwa, for which he has my gratitude. When he initially pointed out the error I awarded him a $50 bounty; now that the implications are confirmed I’ve upped that to $250. In two weeks an additional

en-gb

16:02

“SB 1047 Is Weakened” by Zvi

LessWrong (30+ Karma) ·

2024/06/06

It looks like Scott Weiner's SB 1047 is now severely weakened.Some of the changes are good clarifications. One is a big very welcome fix. The one I call The Big Flip is something very different. It is mind boggling that we can have a political system where a bill can overwhelmingly pass the California senate, and then a bunch of industry lobbyists and hyperbolic false claims can make Scott Weiner feel bullied into making these changes. I will skip the introduction, since those

en-gb

11:41

“rapid psychological growth” by Chipmonk

LessWrong (30+ Karma) ·

2024/06/06

This is a link post.After a one-hour session with an exceptional counselor, I never suffered over that romantic incident again. Although, that's inaccurate, I also had 2x half-hour relapses in following month.After a few more sessions, I stopped doing depression.I brought the rest of my anxieties to that counselor over the following year, and…Radically effective and rapid psychological growth is possible with the right combination of counselor and method. But this is rare in 2024! Introspection that

en-gb

0:34

“Calculating Natural Latents via Resampling” by...

LessWrong (30+ Karma) ·

2024/06/06

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 6th, 2024 Source: https://www.lesswrong.com/posts/NHKCtSXgFieDAyWt2/calculating-natural-latents-via-resampling --- Narrated by TYPE III AUDIO.

en-gb

4:06

“Announcing ILIAD — Theoretical AI Alignment...

LessWrong (30+ Karma) ·

2024/06/05

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.We are pleased to announce ILIAD — a 5-day conference bringing together 100+ researchers to build strong scientific foundations for AI alignment. ***Apply to attend by June 30!*** When: Aug 28 - Sep 3, 2024Where: @Lighthaven (Berkeley, US)What: A mix of topic-specific tracks, and unconference style programming, 100+ attendees. Topics will include Singular Learning Theory, Agent Foundations, Causal Incentives,

en-gb

2:05

“Former OpenAI Superalignment Researcher:...

LessWrong (30+ Karma) ·

2024/06/05

This is a link post.The AGI race has begun. We are building machines that can think and reason. By 2025/26, these machines will outpace many college graduates. By the end of the decade, they will be smarter than you or I; we will have superintelligence, in the true sense of the word. In the link provided, Leopold Aschenbrenner explains why he believes AGI is likely to arrive within the decade, with superintelligence following soon after. He does so in some detail; the website is well-organized, but

en-gb

25:46

“On ‘first critical tries’ in AI alignment” by Joe...

LessWrong (30+ Karma) ·

2024/06/05

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.People sometimes say that AI alignment is scary partly (or perhaps: centrally) because you have to get it right on the “first critical try,” and can’t learn from failures.[1] What does this mean? Is it true? Does there need to be a “first critical try” in the relevant sense? I’ve sometimes felt confused about this, so I wrote up a few thoughts to clarify.I start with a few miscellaneous conceptual points. I then

en-gb

45:07

“Takeoff speeds presentation at Anthropic” by Tom...

LessWrong (30+ Karma) ·

2024/06/05

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a lightly edited transcript of a presentation that I (Tom Davidson) gave at Anthropic in September 2023. See also the video recording, or the slides.None of the content necessarily reflects the views of Anthropic or anyone who works there.Summary: Software progress – improvements in pre-training algorithms, data quality, prompting strategies, tooling, scaffolding, and all other sources of AI progress other

en-gb

24:17

“Evidence of Learned Look-Ahead in a Chess-Playing...

LessWrong (30+ Karma) ·

2024/06/05

Paper authors: Erik Jenner, Shreyas Kapur, Vasil Georgiev, Cameron Allen, Scott Emmons, Stuart RussellTL;DR: We released a paper with IMO clear evidence of learned look-ahead in a chess-playing network (i.e., the network considers future moves to decide on its current one). This post shows some of our results, and then I describe the original motivation for the project and reflect on how it went. I think the results are interesting from a scientific and perhaps an interpretability perspective, but

en-gb

4:05

“Just admit that you’ve zoned out” by joec

LessWrong (30+ Karma) ·

2024/06/04

Summary: Zoning out is difficult to avoid and common, zoning out without admitting it hurts your comprehension, therefore you should admit that you zoned out and ask people to repeat things.If you’re anything like me, you’ve “zoned out” before. You’ve probably even zoned out when you’re trying to learn something interesting. In fact, I’d bet that you’ve zoned out when listening to someone you respect teaching you something interesting, and that you didn’t admit it, and that this left you with a gap

en-gb

24:46

“[Paper] Stress-testing capability elicitation by...

LessWrong (30+ Karma) ·

2024/06/04

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.The paper is by Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov and David Krueger. This post was written by Fabien and Ryan, and may not reflect the views of Dmitrii and David.Scheming models might try to perform less capably than they are able to (sandbag). They might do this to make evaluations underestimate danger, slow down promising safety work, or cause issues with debate or

en-gb

4:56

“in defense of Linus Pauling” by bhauth

LessWrong (30+ Karma) ·

2024/06/04

This is a link post.Linus Pauling was a chemist who won a Nobel Prize in Chemistry in 1954. He later became well-known for advocating large doses of Vitamin C.I've heard that advocacy referred to as a cautionary tale, but I've long had a bit of sympathy for Linus, and I'm writing this post to explain how and why. mainstream nutrition One reason for my sympathy for Linus is that I've heard him used as an example of why you shouldn't go off on your own instead of trusting mainstream views in a

en-gb

6:50

“(Not) Derailing the LessOnline Puzzle Hunt” by Error

LessWrong (30+ Karma) ·

2024/06/04

(spoiler alert: may meta-spoil future iterations of the LOPH, if you haven’t already read other posts about it) I knew early on that I wouldn’t be able to finish the LessOnline puzzle hunt. I contributed to solving two of the first six puzzles, each of which revealed the combination to a locked box. Each box contained medallions for the solvers and a QR code. The QR codes led to the second layer of a larger meta-puzzle. On discovering the existence of the meta-puzzle, I knew I would have to drop

en-gb

11:48

“Companies’ safety plans neglect risks from scheming...

LessWrong (30+ Karma) ·

2024/06/03

Without countermeasures, a scheming AI could escape. A safety case (for deployment) is an argument that it is safe to deploy a particular AI system in a particular way.[1] For any existing LM-based system, the developer can make a great safety case by demonstrating that the system does not have dangerous capabilities.[2] No dangerous capabilities is a straightforward and solid kind of safety case. For future systems with dangerous capabilities, a safety case will require an argument that the system

en-gb

14:47

“AI catastrophes and rogue deployments” by Buck

LessWrong (30+ Karma) ·

2024/06/03

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.[Thanks to Aryan Bhatt, Ansh Radhakrishnan, Adam Kaufman, Vivek Hebbar, Hanna Gabor, Justis Mills, Aaron Scher, Max Nadeau, Ryan Greenblatt, Peter Barnett, Fabien Roger, and various people at a presentation of these arguments for comments. These ideas aren’t very original to me; many of the examples of threat models are from other people.]In this post, I want to introduce the concept of a “rogue deployment” and

en-gb

11:43

“Comments on Anthropic’s Scaling Monosemanticity” by...

LessWrong (30+ Karma) ·

2024/06/03

These are some of my notes from reading Anthropic's latest research report, Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet. TL;DRIn roughly descending order of importance: Its great that Anthropic trained an SAE on a production-scale language model, and that the approach works to find interpretable features. Its great those features allow interventions like the recently-departed Golden Gate Claude. I especially like the code bug feature.I worry that naming features

en-gb

1:12

“Drexler’s Nanosystems is now available online” by...

LessWrong (30+ Karma) ·

2024/06/02

This is a link post.You can read the book on nanosyste.ms."Anyone who needs to talk AGI or AGI strategy needs to understand this table from Drexler's _Nanosystems_, his PhD thesis accepted by MIT which won technical awards. These are calculation outputs; you need to have seen how Drexler calculated them."- Eliezer Yudkowsky[1]The book won the 1992 Award for Best Computer Science Book. The AI safety community often references it, as it describes a lower bound on what intelligence should be able to

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