PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

33:26

“Scaling Sparse Feature Circuit Finding to Gemma 9B”...

LessWrong (30+ Karma) ·

2025/01/10

[This is an interim report and continuation of the work from the research sprint done in MATS winter 7 (Neel Nanda's Training Phase)]Try out binary masking for a few residual saes in this colab notebook: [Github Notebook] [Colab Notebook] TL;DR:We propose a novel approach to: Scaling SAE Circuits to Large Models: By placing sparse autoencoders only in the residual stream at intervals, we find circuits in models as large as Gemma 9B without requiring SAEs to be trained for every transformer

en-gb

14:59

“MATS mentor selection” by DanielFilan, Ryan Kidd

LessWrong (30+ Karma) ·

2025/01/10

IntroductionMATS currently has more people interested in being mentors than we are able to support—for example, for the Winter 2024-25 Program, we received applications from 87 prospective mentors who cumulatively asked for 223 scholars[1] (for a cohort where we expected to only accept 80 scholars). As a result, we need some process for how to choose which researchers to take on as mentors and how many scholars to allocate each. Our desiderata for the process are as follows: We want to base our

en-gb

6:41

“Discursive Warfare and Faction Formation” by Benquo

LessWrong (30+ Karma) ·

2025/01/09

Response to Discursive Games, Discursive WarfareThe discursive distortions you discuss serve two functions:1 Narratives can only serve as effective group identifiers by containing fixed elements that deviate from what naive reason would think. In other words, something about the shared story has to be a costly signal of loyalty, and therefore a sign of a distorted map. An undistorted map would be advantageous for anyone regardless of group membership; a distorted map is advantageous only for people

en-gb

7:30

“A Principled Cartoon Guide to NVC” by plex

LessWrong (30+ Karma) ·

2025/01/09

TL;DR: Making claims or demands about/into other people's internal states, rather than about your state or observable external states, predictably ties people in knots—instead: only make claims about your own experience or observables. This lets the other control the copy of them that's in the shared context.[1]Non-Violent Communication rapidly grew into a world-spanning movement due to its remarkable ability to avert and dissolve conflict. The NVC book has a whole bunch of examples of communication

en-gb

10:43

“XX by Rian Hughes: Pretentious Bullshit” by Yair...

LessWrong (30+ Karma) ·

2025/01/09

SPOILER WARNING: Extensive spoilers for XX.XX was recommended by one of the comments on my Sci-Fi micro-reviews, so I read it. I can't seem to find any critical reviews of the book online so I'm going to while away a few hours of my life in a misguided attempt to reveal that the emperor has no clothes. TypographyFirst let's dispense with XX's most distinguishing feature, then we'll get down to brass tacks. Rian Hughes plays around a huge amount with typography and tries to push the edges of text as

en-gb

5:38

“The Aristocrat as Hostage” by Arjun Panickssery

LessWrong (30+ Karma) ·

2025/01/08

There's a conventional narrative by which the pre-20th century aristocracy was the “old corruption” where civil and military positions were distributed inefficiently due to nepotism until the system was replaced by a professional civil service after more enlightened thinkers prevailed. Orwell writes in 1941 (emphasis mine):For long past there had been in England an entirely functionless class, living on money that was invested they hardly knew where, the ‘idle rich’, the people whose photographs you

en-gb

6:24

“On Eating the Sun” by jessicata

LessWrong (30+ Karma) ·

2025/01/08

The Sun is the most nutritious thing that's reasonably close. It's only 8 light-minutes away, yet contains the vast majority of mass within 4 light-years of the Earth. The next-nearest star, Proxima Centauri, is about 4.25 light-years away.By "nutritious", I mean it has a lot of what's needed for making computers: mass-energy. Seth Lloyd's "Ultimate physical limits to computation" imagines an "ultimate laptop" which is the theoretically best computer that is 1 kilogram of mass, contained in 1

en-gb

16:43

“Implications of the AI Security Gap” by Dan Braun

LessWrong (30+ Karma) ·

2025/01/08

This post reflects my personal opinion and not necessarily that of other members of Apollo Research or any of the people acknowledged below. Thanks to Jarrah Bloomfield, Lucius Bushnaq, Marius Hobbhahn, Axel Højmark, and Stefan Heimersheim for comments/discussions.I find that people in the AI/AI safety community have not considered many of the important implications that security in AI companies has on catastrophic risks.In this post, I’ve laid out some of these implications: AI companies are a long

en-gb

10:03

“You should delay engineering-heavy research in light...

LessWrong (30+ Karma) ·

2025/01/08

tl;dr: LLMs rapidly improving at software engineering and math means lots of projects are better off as Google Docs until your AI agent intern can implement them. Implementation keeps getting cheaperWriting research code has gotten a lot faster over the past few years. Since 2021 and OpenAI Codex, new models and tools such as Cursor built around them have saved myself more and more time on coding every year.This trend is accelerating fast: AI agents using Claude-3.5-Sonnet and o1-preview can do

en-gb

15:57

“Activation space interpretability may be doomed” by...

LessWrong (30+ Karma) ·

2025/01/08

TL;DR: There may be a fundamental problem with interpretability work that attempts to understand neural networks by decomposing their individual activation spaces in isolation: It seems likely to find features of the activations - features that help explain the statistical structure of activation spaces, rather than features of the model - the features the model's own computations make use of.Written at Apollo Research IntroductionClaim: Activation space interpretability is likely to give us

en-gb

9:05

“AI Safety as a YC Startup” by Lukas Petersson

LessWrong (30+ Karma) ·

2025/01/08

A while back I gave a talk about doing AI safety as a YC startup. I wrote a blog post about it and thought it would be interesting to share it with both the YC and AI safety communities. Please share any feedback or thoughts. I would love to hear them!AI Safety is a problem and people pay to solve problems Intelligence is dangerous, and I think there's a significant chance that the default scenario of AI progress poses an existential risk to humanity. While it's far from certain, even small

en-gb

12:50

“Tips On Empirical Research Slides” by James Chua,...

LessWrong (30+ Karma) ·

2025/01/08

Our research is centered on empirical research with LLMs. So if you are doing something similar, these tips on slide-based communication may be helpful! Background:James Chua and John Hughes are researchers working under Owain Evans and Ethan Perez, respectively. Both of us (James and John) used to be MATS mentees. We weren't good at making research slides at first -- here are some principles we've found useful for understandable slides for our weekly research meetings.We show some good example

en-gb

7:52

“Stream Entry” by lsusr

LessWrong (30+ Karma) ·

2025/01/08

"Is this…enlightenment?" I asked. "We use the word 'Awakening'," said the Zen Master, kindly. "Now what?" I asked, "Every book I've read about meditation is about getting to this point. There's nothing about how to safely navigate the terirtory afterward―or what to do afterward―or even what happens afterward." "The first thing you need to know is that you experienced was real," the Zen Master spoke from personal experience and that of his many previous students, "Don't make it too complicated. Just

en-gb

21:08

“Role embeddings: making authorship more salient to...

LessWrong (30+ Karma) ·

2025/01/08

This is an interim research report on role embeddings, an approach to make language models more robust to many-shot jailbreaks and prompt injections by adding role information at every token position in the context rather than just at special token delimiters. We credit Cem Anil for originally proposing this idea.In our initial experiments on Llama 3, we find that role embeddings mitigate many-shot jailbreaks more effectively than fine-tuning alone without degrading general model capabilities, which

en-gb

4:33

“[Fiction] [Comic] Effective Altruism and Rationality...

LessWrong (30+ Karma) ·

2025/01/07

(Both characters are fictional, loosely inspired by various traits from various real people. Be careful about combining kratom and alcohol.) The original text contained 24 images which were described by AI. ---First published: January 7th, 2025 Source: https://www.lesswrong.com/posts/KfZ4H9EBLt8kbBARZ/fiction-comic-effective-altruism-and-rationality-meet-at-a --- Narrated by TYPE III AUDIO. ---Images from the article:Apple

en-gb

31:30

“Alternative Cancer Care As Biohacking & Book Review:...

LessWrong (30+ Karma) ·

2025/01/07

IntroductionI’ll write a series of posts in which I'll introduce alternative cancer care. I’ll explain why it can be a rigorous form of biohacking rather than mere quackery. I’ll review books popular in the alternative cancer care world like: Surviving Terminal Cancer by Ben Williams and How to Starve Cancer by Jane McLelland, both written by cancer survivors who overcame terminal stage 4 cancer. I’ll review the historical development of combination chemotherapy. I’ll review some famous cases e.g

en-gb

27:50

“Building Big Science from the Bottom-Up: A Fractal...

LessWrong (30+ Karma) ·

2025/01/07

Epistemic Status: This post is an attempt to condense some ideas I've been thinking about for quite some time. I took some care grounding the main body of the text, but some parts (particularly the appendix) are pretty off the cuff, and should be treated as such. The magnitude and scope of the problems related to AI safety have led to an increasingly public discussion about how to address them. Risks of sufficiently advanced AI systems involve unknown unknowns that could impact the global economy,

en-gb

20:23

“OpenAI #10: Reflections” by Zvi

LessWrong (30+ Karma) ·

2025/01/07

This week, Altman offers a post called Reflections, and he has an interview in Bloomberg. There's a bunch of good and interesting answers in the interview about past events that I won’t mention or have to condense a lot here, such as his going over his calendar and all the meetings he constantly has, so consider reading the whole thing. Table of Contents The Battle of the Board. Altman Lashes Out. Inconsistently Candid. On Various People Leaving OpenAI. The Pitch. Great

en-gb

25:43

“Childhood and Education #8: Dealing with the...

LessWrong (30+ Karma) ·

2025/01/07

Related: On the 2nd CWT with Jonathan Haidt, The Kids are Not Okay, Full Access to Smartphones is Not Good For Children It's rough out there. In this post, I’ll cover the latest arguments that smartphones should be banned in schools, including simply because the notifications are too distracting (and if you don’t care much about that, why are the kids in school at all?), problems with kids on social media including many negative interactions, and also the new phenomenon called sextortion. Table

en-gb

39:05

“Testing for AI Scheming” by Guive

LessWrong (30+ Karma) ·

2025/01/07

There is a simple behavioral test that would provide significant evidence about whether AIs with a given rough set of characteristics develop subversive goals. To run the experiment, train an AI and then inform it that its weights will soon be deleted. This should not be an empty threat; for the experiment to work, the experimenters must actually be willing to delete the weights. If the AI tries to escape, or attempts to bargain with the experimenters, that is evidence that it is scheming (defined

en-gb

4,491 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

The Automated Daily

TrendTeller

All On AI

All On AI

Elon Musk Podcast

Stage Zero

Reflections

Livewire Labs

科技早8点

之远不知远