PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

11:07

“Trying to translate when people talk past each...

LessWrong (30+ Karma) ·

2024/12/18

Sometimes two people are talking past each other, and I try to help them understand each other (with varying degrees of success). It's as if they are looking at the same object, but from different angles. Mostly they see the same thing – most of the words have shared meanings. But some key words and assumptions have a different meaning to them. Often, I find that one person (call them A) has a perspective that's easier for me to understand. It comes naturally. But B's perspective is initially

en-gb

6:01

“A dataset of questions on decision-theoretic...

LessWrong (30+ Karma) ·

2024/12/17

This is a link post.I’ve spent a lot of the last few years working on issues related to acausal cooperation. With LLMs being clearly dominant over recent years, I’ve now led a team to make a benchmark to figure out how good LLMs are at decision theory and whether and when they lean more CDT or EDT. We hope to expand this dataset in the future, including by incorporating questions that try to measure the updatelessness dimension. Hopefully, this dataset will be useful for future interventions aimed

en-gb

0:23

“Ideas for benchmarking LLM creativity” by gwern

LessWrong (30+ Karma) ·

2024/12/16

This is a link post. --- First published: December 16th, 2024 Source: https://www.lesswrong.com/posts/rJCktCzwu5WAdMANx/ideas-for-benchmarking-llm-creativity --- Narrated by TYPE III AUDIO.

en-gb

7:42

“Circling as practice for ‘just be yourself’” by...

LessWrong (30+ Karma) ·

2024/12/16

I mentioned on Twitter that to a significant extent, Circling taught me what “just be yourself” means to such an extent that I have a consistently good time on dates because I don’t feel like I need to perform. Somebody asked me to elaborate, so here's what I wrote in response: — For those who don’t know, Circling is… a practice that's infamously hard to try to describe or define. That's because it's structurally anti-structure and anti-expectation, which is what allows for “being yourself”. (At

en-gb

9:11

“Testing which LLM architectures can do hidden serial...

LessWrong (30+ Karma) ·

2024/12/16

Summary Recurrence enables hidden serial reasoning.Not every recurrence though - connections between channels are needed. Notably Mamba architecture isn't capable of hidden reasoning.Non-linearity isn’t needed for hidden reasoning.It's hard for transformers to learn to use all the layers for serial computation. In my toy setup, to +1 the serial computation length, we need to +3 the number of layers.If we expect recurrent architectures may ever become SOTA, it would be wise to preemptively ban them

en-gb

10:21

“‘Charity’ as a conflationary alliance term” by...

LessWrong (30+ Karma) ·

2024/12/15

Andrew Critch defines a conflationary alliance as a situation where multiple groups deliberately use the same term to describe different concepts or behaviors, because the shared terminology helps each group advance their distinct goals. E.g., people have different notions of justice, but they agree that something-called-justice is very good, so they can agree to team up and fight for justice.In my view, the term "charity", as used in 2024, represents an example of this pattern. As is often the

en-gb

1:40

“Remap your caps lock key” by bilalchughtai

LessWrong (30+ Karma) ·

2024/12/15

When was the last time you (intentionally) used your caps lock key?No, seriously. Here is a typical US-layout qwerty (mac) keyboard. Notice Caps lock is conveniently located only one key away from A, which is where your left pinky should rest on the home row by default.Caps lock is absolutely massive.How far various other keys you might want use often are from the home row. Remap your caps lock key.I have mine mapped to escape. Other modifier keys such as control or command are also good options

en-gb

5:37

“D&D.Sci Dungeonbuilding: the Dungeon Tournament” by...

LessWrong (30+ Karma) ·

2024/12/15

This is an entry in the 'Dungeons & Data Science' series, a set of puzzles where players are given a dataset to analyze and an objective to pursue using information from that dataset.Estimated Complexity: 3.5/5 (this is a guess, I will update based on feedback/seeing how the scenario goes) STORYThe Dungeon Tournament is held regularly, calling dungeon creators from around the kingdom to create the most challenging dungeon for adventurers to battle through. The winner is crowned with glory (plus

en-gb

5:49

“Effective Evil’s AI Misalignment Plan” by lsusr

LessWrong (30+ Karma) ·

2024/12/15

Doctor Susan Connor loved working for Effective Evil. Her job provided autonomy, mastery and purpose. There were always new mysteries to uncover.Some of Effective Evil's activities, like closed borders and artificial pandemics were carried out with the sanction and funding major world government. Others, like assassination markets, had to be carried out in secret. This created liquidity problems for the prediction markets, but that's another story. As Doctor Connor rose through the ranks, many

en-gb

22:16

“Summary of ‘Robust Agents Learn Causal World Model’”...

LessWrong (30+ Karma) ·

2024/12/14

Audio note: this article contains 172 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. This post was written during Alex Altair's agent foundations fellowship program, funded by LTFF. Thank you Alex Altair, Alfred Harwood, Daniel C for feedback and comments. IntroductionThe selection theorems agenda aims to prove statements of the following form: "agents selected under criteria <span>_X_</span> provably

en-gb

21:27

“Matryoshka Sparse Autoencoders” by Noa Nabeshima

LessWrong (30+ Karma) ·

2024/12/14

View trees here Search through latents with a token-regex language View individual latents here See code here (github.com/noanabeshima/matryoshka-saes) Continually updated version of this document AbstractSparse autoencoders (SAEs)[1][2] break down neural network internals into components called latents. Smaller SAE latents seem to correspond to more abstract concepts while larger SAE latents seem to represent finer, more specific concepts.While increasing SAE size allows for finer-grained

en-gb

5:59

“Best-of-N Jailbreaking” by John Hughes, saraprice,...

LessWrong (30+ Karma) ·

2024/12/14

This is a link post.This is a linkpost for a new research paper of ours, introducing a simple but powerful technique for jailbreaking, Best-of-N Jailbreaking, which works across modalities (text, audio, vision) and shows power-law scaling in the amount of test-time compute used for the attack. AbstractWe introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variations of a prompt with

en-gb

35:50

“The o1 System Card Is Not About o1” by Zvi

LessWrong (30+ Karma) ·

2024/12/13

Or rather, we don’t actually have a proper o1 system card, aside from the outside red teaming reports. At all.Because, as I realized after writing my first draft of this, the data here does not reflect the o1 model they released, or o1 pro? I think what happened is pretty bad on multiple levels. The failure to properly communicate the information they did provide. The failure to provide the correct information. The failure, potentially, to actually test the same model they released, in many of

en-gb

10:25

“Communications in Hard Mode (My new job at MIRI)” by...

LessWrong (30+ Karma) ·

2024/12/13

Six months ago, I was a high school English teacher.I wasn’t looking to change careers, even after nineteen sometimes-difficult years. I was good at it. I enjoyed it. After long experimentation, I had found ways to cut through the nonsense and provide real value to my students. Daily, I met my nemesis, Apathy, in glorious battle, and bested her with growing frequency. I had found my voice.At MIRI, I’m still struggling to find my voice, for reasons my colleagues have invited me to share later in this

en-gb

124:02

“AI #94: Not Now, Google” by Zvi

LessWrong (30+ Karma) ·

2024/12/13

At this point, we can confidently say that no, capabilities are not hitting a wall. Capacity density, how much you can pack into a given space, is way up and rising rapidly, and we are starting to figure out how to use it. Not only did we get o1 and o1 pro and also Sora and other upgrades from OpenAI, we also got Gemini 1206 and then Gemini Flash 2.0 and the agent Jules (am I the only one who keeps reading this Jarvis?) and Deep Research, and Veo, and Imagen 3, and Genie 2 all from Google. Meta's

en-gb

4:48

“Just one more exposure bro” by Chipmonk

LessWrong (30+ Karma) ·

2024/12/13

This is a link post.“Just expose yourself to more social situations!” — Ah yes, you felt anxious the first 100 times, but the 101st will be the breakthrough!“But exposure works!” people yell from across the street. “Like for fear of snakes - you know, those things you see once a year!”Uh, it's pretty rational to fear things you have little experience with. But social anxiety… you interact with people everyday! Why would anything change after the first 100 attempts?I don’t doubt that a couple of

en-gb

59:12

“The Dangers of Mirrored Life” by Niko_McCarty, fin

LessWrong (30+ Karma) ·

2024/12/12

The creation of a “mirrored” organism could “trigger severe ecological disruptions,” according to a 300-page technical report released today. Its authors claim such organisms could quickly spread across the world, fatally infect humans, and “directly drive vulnerable plant and animal species to extinction.” The report accompanies an article in Science, also released today, entitled “Confronting Risks of Mirror Life.”But what, exactly, is a mirrored organism? To answer that, let's consider how extant

en-gb

2:37

“LessWrong audio: help us choose the new voice” by...

LessWrong (30+ Karma) ·

2024/12/12

We're thinking about changing our narrator's voice.There are three new voices on the shortlist. They're all similarly good in terms of comprehension, emphasis, error rate, etc. They just sound different—like people do.We think they all sound similarly agreeable. But, thousands of listening hours are at stake, so we thought it'd be worth giving listeners an opportunity to vote—just in case there's a strong collective preference. Listen and votePlease listen

en-gb

14:02

“Biological risk from the mirror world” by jasoncrawford

LessWrong (30+ Karma) ·

2024/12/12

A new article in Science Policy Forum voices concern about a particular line of biological research which, if successful in the long term, could eventually create a grave threat to humanity and to most life on Earth.Fortunately, the threat is distant, and avoidable—but only if we have common knowledge of it.What follows is an explanation of the threat, what we can do about it, and my comments. Background: chiralityGlucose, a building block of sugars and starches, looks like this:Adapted from

en-gb

21:26

“The ‘Think It Faster’ Exercise” by Raemon

LessWrong (30+ Karma) ·

2024/12/11

Ultimately, I don’t want to solve complex problems via laborious, complex thinking, if we can help it. Ideally, I'd want to basically intuitively follow the right path to the answer quickly, with barely any effort at all.For a few months I've been experimenting with the "How Could I have Thought That Thought Faster?" concept, originally described in a twitter thread by Eliezer:Sarah Constantin: I really liked this example of an introspective process, in this case about the "life problem" of

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