PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

20:56

“A gentle introduction to mechanistic anomaly...

LessWrong (30+ Karma) ·

2024/04/04

TL;DR: Mechanistic anomaly detection aims to flag when an AI produces outputs for “unusual reasons.” It is similar to mechanistic interpretability but doesn’t demand human understanding. I give a self-contained introduction to mechanistic anomaly detection from a slightly different angle than the existing one by Paul Christiano (focused less on heuristic arguments and drawing a more explicit parallel to interpretability).Mechanistic anomaly detection was first introduced by the Alignment Research

en-gb

33:35

“Best in Class Life Improvement” by sapphire

LessWrong (30+ Karma) ·

2024/04/04

There is an enormous amount of crappy self-help advice. Most supplements do nothing. However, some substances and practices can dramatically improve your life. It's worth being explicit about what those are in my experience.The American medical system endorses all of these treatments and methods, and you can implement them with a doctor's supervision. The only way I differ from the American medical system is that they operate under a paradigm of treating diseases or perhaps what might be better

en-gb

46:30

“Sparsify: A mechanistic interpretability research...

LessWrong (30+ Karma) ·

2024/04/03

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.Over the last couple of years, mechanistic interpretability has seen substantial progress. Part of this progress has been enabled by the identification of superposition as a key barrier to understanding neural networks (Elhage et al., 2022) and the identification of sparse autoencoders as a solution to superposition (Sharkey et al., 2022; Cunningham et al., 2023; Bricken et al., 2023). From our current vantage

en-gb

32:06

“Notes on Dwarkesh Patel’s Podcast with Sholto...

LessWrong (30+ Karma) ·

2024/04/02

Dwarkesh Patel continues to be on fire, and the podcast notes format seems like a success, so we are back once again. This time the topic is how LLMs are trained, work and will work in the future. Timestamps are for YouTube. Where I inject my own opinions or takes, I do my best to make that explicit and clear. This was highly technical compared to the average podcast I listen to, or that Dwarkesh does. This podcast definitely threated to technically go over my head at times, and some

en-gb

3:17

“Thousands of malicious actors on the future of AI...

LessWrong (30+ Karma) ·

2024/04/02

Announcing the results of a 2024 survey by Convergence Analysis. We’ve just posted the executive summary below, but you can read the full report here. In the largest survey of its kind, Convergence Analysis surveyed 2,779 malicious actors on how they would misuse AI to catastrophic ends. In previous work, we’ve explored the difficulty of forecasting AI risk. Existing attempts rely almost exclusively on data from AI experts and professional forecasters. As a result, the perspectives of perhaps the

en-gb

17:17

“Gradient Descent on the Human Brain” by Jozdien,...

LessWrong (30+ Karma) ·

2024/04/02

TL;DR: Many alignment research proposals often share a common motif: figure out how to enter a basin of alignment / corrigibility for human-level models, and then amplify to more powerful regimes while generalizing gracefully. In this post we lay out a research agenda that comes at this problem from a different direction: if we already have ~human-level systems with extremely robust generalization properties, we should just amplify those directly. We’ll call this strategy “Gradient Descent on the

en-gb

22:03

“Coherence of Caches and Agents” by johnswentworth

LessWrong (30+ Karma) ·

2024/04/02

There's a lot of confusion about what coherence means for agents, and what "coherence theorems" do and don't say about agents. In this post, I'll talk about some particularly simple notions of coherence in a particularly simple setting. We'll see what nontrivial things coherence has to say, at least in a simple kind of environment, starting with an analogous notion of coherence for caches. What Kind Of "Coherence" We're Talking About HereLet's start with a standard CS-101-style example. We write a

en-gb

2:13

“Announcing Suffering For Good” by Garrett Baker

LessWrong (30+ Karma) ·

2024/04/01

TL;DR: We are excited to announce the new animal welfare organization Suffering For Good, a new factory farming charity aimed at vegans, where we use our excess profits to buy suffering offsets--in particular, an enormous number of rats on heroin.For decades, even centuries, us vegans have been trying but failing to get the world to stop eating & torturing sentient minds that can definitely feel pain & suffer. But the global number of such minds tortured & killed just keeps on

en-gb

5:18

“OMMC Announces RIP” by Adam Scholl, aysja

LessWrong (30+ Karma) ·

2024/04/01

At the Omnicide Machine Manufacturing Corporation, we work tirelessly to ensure an omnicide-free future. That's why we’re excited to announce our Responsible Increase Policy (RIP)—our internal protocol for managing any risks that arise as we create increasingly omnicidal machines.Inspired by the risk-management framework used in gain-of-function virology research, our RIP defines a framework of Omnicidal Ability Levels (OAL), reflecting the precautions we plan to take as we release increasingly

en-gb

3:45

“The Evolution of Humans Was Net-Negative for Human...

LessWrong (30+ Karma) ·

2024/04/01

(Epistemic status: publication date is significant.) Some observers have argued that the totality of "AI safety" and "alignment" efforts to date have plausibly had a negative rather than positive impact on the ultimate prospects for safe and aligned artificial general intelligence. This perverse outcome is possible because research "intended" to help with AI alignment can have a larger impact on AI capabilities, moving existentially-risky systems closer to us in time without making corresponding

en-gb

9:21

“A Selection of Randomly Selected SAE Features” by...

LessWrong (30+ Karma) ·

2024/04/01

Epistemic status - self-evident.In this post, we interpret a small sample of Sparse Autoencoder features which reveal meaningful computational structure in the model that is clearly highly researcher-independent and of significant relevance to AI alignment. MotivationRecent excitement about Sparse Autoencoders (SAEs) has been mired by the following question: Do SAE features reflect properties of the model, or just capture correlational structure in the underlying data distribution?While a full

en-gb

2:29

“Apply to be a Safety Engineer at Lockheed Martin!”...

LessWrong (30+ Karma) ·

2024/04/01

Are you passionate about ensuring the safety and reliability of the world's most lethal and cutting-edge weaponry? Does the idea of creating technology and then working out its impacts excite you? Do you thrive in dynamic environments where innovation meets rigorous safety standards? If so, you might want to consider joining the team at Lockheed Martin (LM), global leaders in advanced weapon systems development!Position overview and background:As a Safety Engineer specializing in advanced weaponry

en-gb

2:55

[Linkpost] “Introducing Open Asteroid Impact” by Linch

LessWrong (30+ Karma) ·

2024/04/01

This is a linkpost for https://openasteroidimpact.org/ “That which does not kill us makes us stronger.” Hillary Clinton, who is still alive I'm proud and excited to announce the founding of my new startup, Open Asteroid Impact, where we redirect asteroids towards Earth for the benefit of humanity. Our mission is to have as high an impact as possible. Below, I've copied over the one-pager I've sent potential investors and early employees: Name: Open Asteroid Impact Launch Date: April 1 2024

en-gb

22:40

“The Story of ‘I Have Been A Good Bing’” by habryka,...

LessWrong (30+ Karma) ·

2024/04/01

Rationality is Systematized Winning, so rationalists should win. We’ve tried saving the world from AI, but that's really hard and we’ve had … mixed results. So let's start with something that rationalists should find pretty easy: Becoming Cool! I don’t mean, just, like, riding a motorcycle and breaking hearts level of cool. I mean like the first kid in school to get a Tamagotchi, their dad runs the ice cream truck and gives you free ice cream and, sure, they ride a motorcycle. I mean that kind of

en-gb

2:15

“SAE-VIS: Announcement Post” by CallumMcDougall,...

LessWrong (30+ Karma) ·

2024/03/31

This is a post to officially announce the sae-vis library, which was designed to create feature dashboards like those from Anthropic's research.Summary. There are 2 types of visualisations supported by this library: feature-centric and prompt-centric.The feature-centric vis is the standard from Anthropic's post, it looks like the image below. There's an option to navigate through different features via a dropdown in the top left.You can see the interactive version at the GitHub repo, at

en-gb

14:44

“The Best Tacit Knowledge Videos on Every Subject” by...

LessWrong (30+ Karma) ·

2024/03/31

TL;DRTacit knowledge is extremely valuable. Unfortunately, developing tacit knowledge is usually bottlenecked by apprentice-master relationships. Tacit Knowledge Videos could widen this bottleneck. This post is a Schelling point for aggregating these videos—aiming to be The Best Textbooks on Every Subject for Tacit Knowledge Videos. Scroll down to the list if that's what you're here for. Post videos that highlight tacit knowledge in the comments and I’ll add them to the post. Experts in the videos

en-gb

4:47

“My simple AGI investment & insurance strategy” by lc

LessWrong (30+ Karma) ·

2024/03/31

TL;DR: Options traders think it's extremely unlikely that the stock market will appreciate more than 30 or 40 percent over the next two to three years, as it has over the last year. So they will sell you the option to buy current indexes for 30 or 40% above their currently traded value for very cheap.But slow takeoff, or expectations of one, would almost certainly cause the stock market to rise dramatically. Like many people, I think institutional market makers are basically not pricing this in.To

en-gb

11:26

[Linkpost] “Metascience of the Vesuvius Challenge” by...

LessWrong (30+ Karma) ·

2024/03/30

This is a linkpost for https://www.maximum-progress.com/p/metascience-of-the-vesuvius-challengeThe Vesuvius Challenge is a million+ dollar contest to read 2,000 year old text from charcoal-papyri using particle accelerators and machine learning. The scrolls come from the ancient villa town of Herculaneum, nearby Pompeii, which was similarly buried and preserved by the eruption of Mt. Vesuvius. The prize fund comes from tech entrepreneurs and investors Nat Friedman, Daniel Gross, and several other

en-gb

11:56

“Back to Basics: Truth is Unitary” by lsusr

LessWrong (30+ Karma) ·

2024/03/30

It was a dark and stormy night.The prospect held the front of his cloak tight to his chest. He stumbled, fell over into the mud, and picked himself back up. Shivering, he slammed his body against the front doors of the Temple and collapsed under its awning. He picked himself up and slammed his fists against the double ironwood doors. He couldn't hear his own knocks above the gale. He banged harder, then with all his strength. "Hello! Is anyone in there? Does anyone still tend the Fire?" he

en-gb

13:20

“Your LLM Judge may be biased” by rachelAF, Henry...

LessWrong (30+ Karma) ·

2024/03/30

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.Abstract. AI safety researchers often rely on LLM “judges” to qualitatively evaluate the output of separate LLMs. We try this for our own interpretability research, but find that our LLM judges are often deeply biased. For example, we use Llama2 to judge whether movie reviews are more “(A) positive” or “(B) negative”, and find that it almost always answers “(B)”, even when we switch the labels or order of these

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