PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

33:26

“Vipassana Meditation and Active Inference: A...

LessWrong (30+ Karma) ·

2024/03/24

I want to thank Jan Kulveit, Tomáš Gavenčiak, and Jonathan Shock for their extensive feedback and ideas they contributed to this work and for Josh Burgener and Yusuf Heylen for their proofreading and comments. I would also like to acknowledge the Epistea Residency and its organisers where much of the thinking behind this work was done.This post aims to build towards a theory of how meditation alters the mind based on the ideas of active inference (ActInf). ActInf has been growing in its promise as a

en-gb

14:50

“General Thoughts on Secular Solstice” by Jeffrey...

LessWrong (30+ Karma) ·

2024/03/24

I attended Secular Solstice in Berkeley last December. My perspective is quite unusual: I live in a rationalist group house and work at an AI safety office, but I also am a Christian and attend church every week.[1]I was originally not planning on going to Solstice, but a decent number of people (~5) told me in person that they would be particularly interested in my opinions of it. I realized that I was interested in learning what I would think of it too, so I went.I took notes on my thoughts

en-gb

4:36

“Dangers of Closed-Loop AI” by Gordon Seidoh Worley

LessWrong (30+ Karma) ·

2024/03/23

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.In control theory, an open-loop (or non-feedback) system is one where inputs are independent of outputs. A closed-loop (or feedback) system is one where outputs are input back into the system.In theory, open-loop systems exist. In reality, no system is truly open-loop because systems are embedded in the physical world where isolation of inputs from outputs cannot be guaranteed. Yet in practice we can build systems

en-gb

3:40

“A Teacher vs. Everyone Else” by ronak69

LessWrong (30+ Karma) ·

2024/03/23

A repairer wants your stuff to break down, A doctor wants you to get ill, A lawyer wants you to get in conflicts, A farmer wants you to be hungry, But there is only a teacher who wants you to learn.Of course you see what is wrong with the above "argument / meme / good-thought". But the first time I came across this meme, I did not.Until a month or two ago when this meme appeared in my head again and within seconds I discarded it away as fallacious reasoning. What was the difference this time? That I

en-gb

127:28

“AI #56: Blackwell That Ends Well” by Zvi

LessWrong (30+ Karma) ·

2024/03/23

Hopefully, anyway. Nvidia has a new chip.Also Altman has a new interview. And most of Inflection has new offices inside Microsoft. Table of Contents Introduction. Table of Contents. Language Models Offer Mundane Utility. Open the book. Clauding Along. Claude continues to impress. Language Models Don’t Offer Mundane Utility. What are you looking for? Fun With Image Generation. Stable Diffusion 3 paper. Deepfaketown and Botpocalypse Soon. Jesus Christ. They

en-gb

2:44

“ChatGPT can learn indirect control” by Raymond D

LessWrong (30+ Karma) ·

2024/03/22

Here's a very neat twitter thread: the author sends various multimodal models screenshots of the conversation he's currently having with them, and asks them to describe the images. Most models catch on fast: the author describes this as them passing the mirror test.I liked the direction, so I wanted to check if ChatGPT could go from recognising that the images are causally downstream of it to actually exercising control over the images. I did this by challenging it to include certain text in the

en-gb

0:26

[Linkpost] “Vernor Vinge, who coined the term...

LessWrong (30+ Karma) ·

2024/03/21

This is a linkpost for https://arstechnica.com/information-technology/2024/03/vernor-vinge-father-of-the-tech-singularity-has-died-at-age-79/ --- First published: March 21st, 2024 Source: https://www.lesswrong.com/posts/BYAo8Yvxg2tsCY2Me/vernor-vinge-who-coined-the-term-technological-singularity Linkpost URL:https://arstechnica.com/information-technology/2024/03/vernor-vinge-father-of-the-tech-singularity-has-died-at-age-79/ ---

en-gb

81:49

“On green” by Joe Carlsmith

LessWrong (30+ Karma) ·

2024/03/21

(Cross-posted from my website. Podcast version here, or search for "Joe Carlsmith Audio" on your podcast app. This essay is part of a series that I'm calling "Otherness and control in the age of AGI." I'm hoping that the individual essays can be read fairly well on their own, but see here for brief summaries of the essays that have been released thus far. Warning: spoilers for Yudkowsky's "The Sword of the Good.") "The Creation" by Lucas Cranach (image source here) The colors of the wheel I've

en-gb

18:25

[Linkpost] “‘Deep Learning’ Is Function...

LessWrong (30+ Karma) ·

2024/03/21

This is a linkpost for http://zackmdavis.net/blog/2024/03/deep-learning-is-function-approximation/ A Surprising Development in the Study of Multi-layer Parameterized Graphical Function Approximators As a programmer and epistemology enthusiast, I've been studying some statistical modeling techniques lately! It's been boodles of fun, and might even prove useful in a future dayjob if I decide to pivot my career away from the backend web development roles I've taken in the past. More specifically, I've

en-gb

1:45

[Linkpost] “DeepMind: Evaluating Frontier Models for...

LessWrong (30+ Karma) ·

2024/03/21

This is a linkpost for https://arxiv.org/abs/2403.13793To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new “dangerous capability” evaluations and pilot them on Gemini 1.0 models. Our evaluations cover four areas: (1) persuasion and deception; (2) cyber-security; (3) self-proliferation; and (4) self-reasoning. We do not find evidence of strong dangerous capabilities in the models we evaluated, but we

en-gb

77:09

“On the Gladstone Report” by Zvi

LessWrong (30+ Karma) ·

2024/03/21

Like the the government-commissioned Gladstone Report on AI itself, there are two sections here. First I cover the Gladstone Report's claims and arguments about the state of play, including what they learned talking to people inside the labs. I mostly agree with their picture and conclusions, both in terms of arguments and reported findings, however I already mostly agreed. If these arguments and this information is new to someone, and the form of a government-backed report helps them process it

en-gb

23:19

“Stagewise Development in Neural Networks” by Jesse...

LessWrong (30+ Karma) ·

2024/03/20

TLDR: This post accompanies The Developmental Landscape of In-Context Learning by Jesse Hoogland, George Wang, Matthew Farrugia-Roberts, Liam Carroll, Susan Wei and Daniel Murfet (2024), which shows that in-context learning emerges in discrete, interpretable developmental stages, and that these stages can be discovered in a model- and data-agnostic way by probing the local geometry of the loss landscape. Four months ago, we shared a discussion here of a paper which studied stagewise development in

en-gb

99:04

“Monthly Roundup #16: March 2024” by Zvi

LessWrong (30+ Karma) ·

2024/03/20

AI developments have picked up the pace. That does not mean that everything else stopped to get out of the way. The world continues. Do I have the power? Emmett Shear speaking truth: Wielding power is of course potentially dangerous and it should be done with due care, but there is no virtue in refusing the call. There is also an art to avoiding power, and some key places to exercise it. Be keenly aware of when having power in a given context would ruin everything. Natural General

en-gb

37:12

“Natural Latents: The Concepts” by johnswentworth,...

LessWrong (30+ Karma) ·

2024/03/20

Suppose our old friends Alice and Bob decide to undertake an art project. Alice will draw a bunch of random purple and green lines on a piece of paper. That will be Alice's picture (A). She’ll then make a copy, erase all the purple lines, and send the result as a message (M) to Bob. Bob then generates his own random purple lines, and adds them to the green lines from Alice, to create Bob's picture (B). The two then frame their two pictures and hang them side-by-side to symbolize something something

en-gb

1:34

“New report: Safety Cases for AI” by joshc

LessWrong (30+ Karma) ·

2024/03/20

Here's the Tweet thread: https://twitter.com/joshua_clymer/status/1770467746951868889The idea for this paper occurred to me when I saw Buck Shlegeris' MATS stream on "Safety Cases for AI." How would one justify the safety of advanced AI systems? This question is fundamental. It informs how RSPs should be designed and what technical research is useful to pursue.For a long time, researchers have (implicitly or explicitly) discussed ways to justify that AI systems are safe, but much of this content is

en-gb

9:08

[Linkpost] “Increasing IQ by 10 Points is Possible”...

LessWrong (30+ Karma) ·

2024/03/19

This is a linkpost for https://morelucid.substack.com/p/increasing-iq-by-10-points-is-possibleA while ago I wrote how I managed to add 13 points to my IQ (as measured by the mean between 4 different tests).I had 3 “self-experimenters” follow my instructions in San Francisco. One of them dropped off, since, surprise surprise, the intervention is hard.The other two had an increase of 11 and 10 points in IQ respectively (using the “fluid” components of each test) and an increase of 9 and 7 respectively

en-gb

7:46

[Linkpost] “Inferring the model dimension of...

LessWrong (30+ Karma) ·

2024/03/19

This is a linkpost for https://arxiv.org/abs/2403.09539A new paper by Finlayson et al. describes how to exploit the softmax bottleneck in large language models to infer the model dimension of closed-source LLMs served to the public via an API. I'll briefly explain the method they use to achieve this and provide a toy model of the phenomenon, though the full paper has many practical details I will elide in the interest of simplicity. I recommend reading the whole paper if this post sounds interesting

en-gb

12:01

“Experimentation (Part 7 of ‘The Sense Of Physical...

LessWrong (30+ Karma) ·

2024/03/19

This is the seventh post in a sequence that demonstrates a complete naturalist study, specifically a study of query hugging (sort of), as described in The Nuts and Bolts of Naturalism. This one demos phase four: Experimentation. For context on this sequence, see the intro post. Reminder that this is meant as reference material.Wait, there's more to this study? But we’ve just discussed the main insight that came out of it, and how it illustrates the point of naturalism. Why is there more?There is

en-gb

4:08

“Neuroscience and Alignment” by Garrett Baker

LessWrong (30+ Karma) ·

2024/03/19

I've been in many conversations where I've mentioned the idea of using neuroscience for outer alignment, and the people who I'm talking to usually seem pretty confused about why I would want to do that. Well, I'm confused about why one wouldn't want to do that, and in this post I explain why.As far as I see it, there are three main strategies people have for trying to deal with AI alignment in worlds where AI alignment is hard. Value alignmentCorrigibilityControl/scalable alignmentIn my opinion,

en-gb

3:05

[Linkpost] “Toki pona FAQ” by dkl9

LessWrong (30+ Karma) ·

2024/03/19

This is a linkpost for https://dkl9.net/essays/toki_pona_faq.htmlWhenever I start telling someone about toki pona, they ask at least some of these questions. So I compile the questions and my answers here.Toki pona is a constructed language notable for having under 200 words. The strange writing that probably prompted you to ask me about it is sitelen pona. How do you say anything with so few words?You refer to most things with multi-word phrases, where some words act as adjectives or adverbs.Toki

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