PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

3:26

“Characterizing stable regions in the residual stream...

LessWrong (30+ Karma) ·

2024/09/26

This is a link post.This research was completed for London AI Safety Research (LASR) Labs 2024. The team was supervised by @Stefan Heimershiem (Apollo Research). Find out more about the program and express interest in upcoming iterations here.This video is a short overview of the project presented on the final day of the LASR Labs. Note that the paper was updated since then.Visualization of stable regions in OLMo-7B during training. Colors represent the similarity of model outputs to those produced

en-gb

65:17

“AI #83: The Mask Comes Off” by Zvi

LessWrong (30+ Karma) ·

2024/09/26

We interrupt Nate Silver week here at Don’t Worry About the Vase to bring you some rather big AI news: OpenAI and Sam Altman are planning on fully taking their masks off, discarding the nonprofit board's nominal control and transitioning to a for-profit B-corporation, in which Sam Altman will have equity.We now know who they are and have chosen to be. We know what they believe in. We know what their promises and legal commitments are worth. We know what they plan to do, if we do not stop

en-gb

9:48

“The 2024 Petrov Day Scenario” by Ben Pace, Raemon

LessWrong (30+ Karma) ·

2024/09/26

Today we honor the actions of Stanislav Petrov (1939 – 2017) once again.Half an hour past midnight on September 26, 1983, he saw the first apparent launch on his computer monitor in a glass-walled room on the top floor of the Ballistic Missile Early Warning System (BMEWS) command and control post. The warning system was by now showing five missile launches in the U.S., headed toward the Soviet Union."The main computer wouldn't ask me [what to do] - it was made so that it wouldn't even ask. It was

en-gb

33:04

“[Intuitive self-models] 2. Conscious Awareness” by...

LessWrong (30+ Karma) ·

2024/09/25

2.1 Post summary / Table of contentsThis is the second of a series of eight blog posts, which I’ll be serializing over the next month or two. (Or email or DM me if you want to read the whole thing right now.)The previous post laid some groundwork for talking about intuitive self-models. Now we’re jumping right into the deep end: the intuitive concept of “conscious awareness” (or “awareness” for short). Some argue (§1.6.2) that if we can fully understand why we have an “awareness” concept, then we

en-gb

44:10

“How to prevent collusion when using untrusted models...

LessWrong (30+ Karma) ·

2024/09/25

Suppose you’ve trained a really clever AI model, and you’re planning to deploy it in an agent scaffold that allows it to run code or take other actions. You’re worried that this model is scheming, and you’re worried that it might only need to take a small number of actions to get to a dangerous and hard-to-reverse situation like exfiltrating its own weights. Problems that the AI can cause with small numbers of actions are particularly hard to address with standard safety techniques, because by

en-gb

7:14

“[Paper] A is for Absorption: Studying Feature...

LessWrong (30+ Karma) ·

2024/09/25

This research was completed for London AI Safety Research (LASR) Labs 2024. The team was supervised by Joseph Bloom (Decode Research). Find out more about the programme and express interest in upcoming iterations here.This high level summary will be most accessible to those with relevant context including an understanding of SAEs. The importance of this work rests in part on the surrounding hype, and potential philosophical issues. We encourage readers seeking technical details to read the paper on

en-gb

18:26

“A Path out of Insufficient Views ” by Unreal

LessWrong (30+ Karma) ·

2024/09/25

In appreciation of @zhukeepa's willingness to discuss spirituality on LessWrong, I will share some stories of my own. I grew up as a Christian in the USA and took it seriously. Upon taking a World History class in my freshman year at a secular high school (quite liberal, quite prestigious), I learned that there were a number of major religions, and many of them seemed to contain a lot of overlap. It became clear to me, suddenly, that religions were man-made. None of them seemed to have a real claim

en-gb

52:26

“What are the best arguments for/against AIs being...

LessWrong (30+ Karma) ·

2024/09/24

Awhile ago, Nate Soares wrote the posts Decision theory does not imply that we get to have nice things and Cosmopolitan values don't come free and But why would the AI kill us? Paul Christiano put forth some arguments that "it seems pretty plausible that AI will be at least somewhat 'nice'", similar to how humans are somewhat nice to animals. There was some back-and-forth. More recently we had Eliezer's post ASIs will not leave just a little sunlight for Earth. I have a sense that something feels

en-gb

2:44

“Palisade Research Beliefs and Evidence Bounty ” by...

LessWrong (30+ Karma) ·

2024/09/24

(Cross-posted from the Bountied Rationality Facebook group)Here is a Google Doc that lists 21 important beliefs that Palisade Research has about AI. For each belief, we're looking for the strongest evidence that exists in favor of that idea, and the strongest evidence that exists against it. We'll award at least $20 for the best evidence in favor, and at least $20 for the best evidence against each idea. We'll use our discretion for what we consider the "best" evidence, but the kind of thing we're

en-gb

12:28

“Struggling like a Shadowmoth ” by Raemon

LessWrong (30+ Karma) ·

2024/09/24

This post is probably hazardous for one type of person in one particular growth stage, and necessary for people in a different growth stage, and I don't really know how to tell the difference in advance.If you read it and feel like it kinda wrecked you send me a DM. I'll try to help bandage it. One of my favorite stories growing up was Star Wars: Traitor, by Matthew Stover.The book is short, if you want to read it. Spoilers follow. (I took a look at it again recently and I think it didn't obviously

en-gb

13:46

“Model evals for dangerous capabilities ” by Zach...

LessWrong (30+ Karma) ·

2024/09/23

Testing an LM system for dangerous capabilities is crucial for assessing its risks. Summary of best practicesBest practices for labs evaluating LM systems for dangerous capabilities: Publish resultsPublish questions/tasks/methodology (unless that's dangerous, e.g. CBRN evals; if so, just publish a small subset and offer to share more information with other labs, government, and relevant auditors)Do good elicitation and publish details (or at least demonstrate that your elicitation is good): General

en-gb

19:12

“ASIs will not leave just a little sunlight for Earth...

LessWrong (30+ Karma) ·

2024/09/23

A common claim among e/accs is that, since the solar system is big, Earth will be left alone by superintelligences. A simple rejoinder is that just because Bernard Arnault has $170 billion, does not mean that he'll give you $77.18.Earth subtends only 4.54e-10 = 0.0000000454% of the angular area around the Sun, according to GPT-o1.[1]Asking an ASI to leave a hole in a Dyson Shell, so that Earth could get some sunlight not transformed to infrared, would cost It 4.5e-10 of Its income. This is like

en-gb

3:56

“My 10-year retrospective on trying SSRIs ” by...

LessWrong (30+ Karma) ·

2024/09/23

In 2014 I got on SSRIs the first time, and they were amazing. I wrote online about how I suddenly had energy to do things, could concentrate on stuff, and generally just felt better and happier. I now got a message from someone who’d found my writings and was wondering what my experience with antidepressants was now, 10 years later. I wrote this reply to them, and thought I might as well share it with others: — Hi, that was indeed me! I was on SSRIs for about a year after writing that comment, after

en-gb

2:14

“I’m creating a deep dive podcast episode about the...

LessWrong (30+ Karma) ·

2024/09/22

Hi all! I'm creating a deep dive podcast episode about (the original) Leverage Research (for my podcast, Clearer Thinking). If you worked at (or currently work at) Leverage, or you have had experiences connected to Leverage, and you would like to either potentially:(1) do an interview for the podcast(2) talk to me totally off the record about your experiences (i.e., with your privacy totally protected)Please reach out privately by using my contact form here. Or you can email our podcast (but

en-gb

33:15

“Making Eggs Without Ovaries ” by Niko_McCarty,...

LessWrong (30+ Karma) ·

2024/09/22

This essay was written by @Metacelsus.In March 2023, a research team at Osaka University announced an extraordinary achievement: the production of viable eggs using cells taken from male mice.Building on years of research into stem cells and reproductive development,1 the researchers, led by Professor Katsuhiko Hayashi, developed a method to induce male stem cells to lose their Y chromosome and duplicate the X chromosome, thus becoming female. From there, researchers took the female cells and grew

en-gb

9:05

“On the Role of Proto-Languages ” by adamShimi

LessWrong (30+ Karma) ·

2024/09/22

I’ve been fascinated recently by historical linguistics, and in particular reconstructed proto-languages such as Proto-Indo-European.But what even is a “proto-language”?Well, if we go for the literal operationalization, Wikipedia defines a proto-language as:a postulated ancestral language from which a number of attested languages are believed to have descended by evolution, forming a language family.[…]It is by definition a linguistic reconstruction formulated by applying the comparative method to a

en-gb

13:28

“Another argument against utility-centric alignment...

LessWrong (30+ Karma) ·

2024/09/22

expectation calibrator: freeform draft, posting partly to practice lowering my own excessive standards.So, a few months back, I finally got around to reading Nick Bostrom's Superintelligence, a major player in the popularization of AI safety concerns. Lots of the argument was stuff I'd internalized a long time ago, reading the sequences and even living with AI alignment researchers for a few months. But I wanted to see the circa-2015 risk-case laid out as thorougly as possible, partly as an excusion

en-gb

21:15

“Augmenting Statistical Models with Natural Language...

LessWrong (30+ Karma) ·

2024/09/22

This is a guest post by my student Ruiqi Zhong, who has some very exciting work defining new families of statistical models that can take natural language explanations as parameters. The motivation is that existing statistical models are bad at explaining structured data. To address this problem, we agument these models with natural language parameters, which can represent interpretable abstract features and be learned automatically. Imagine the following scenario: It is the year 3024. We are

en-gb

55:47

“Glitch Token Catalog - (Almost) a Full Clear ” by...

LessWrong (30+ Karma) ·

2024/09/22

This is a collection of every unidentified GPT2 glitch token listed in the third glitch token archaeology post. I was able to find the source of every single one, except for "?????-" and "?????-?????-"[1]. Please tell me if I missed one, or you've discovered one and don't understand where it came from. This isn't meant to be a well-written analysis, just a quick repository of my glitch-hunting observations.I plan on writing up and categorizing all of these in greater detail in future posts. The

en-gb

31:10

“Investigating an insurance-for-AI startup ” by L...

LessWrong (30+ Karma) ·

2024/09/22

We (Flo & Rudolf) spent a month fleshing out the idea of an insurance-for-AI company. We talked to 15 people in the insurance industry, and did 20 customer interviews. We decided not to continue, but we think it's still a very promising idea and that maybe someone else should do this. This post describes our findings. The idea Theory of changeTo reduce AI risks, it would be good if we understood risks well, and if some organisation existed that could incentivise the use of safer AI practices. An

en-gb

4,491 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

The Automated Daily

TrendTeller

Reflections

Livewire Labs

Eli the Computer Guy

Eli the Computer Guy

LessWrong (30+ Karma)

LessWrong

Superkraft KI News | by Jörg Schieb

Jörg Schieb