PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

24:48

“Overview of strong human intelligence amplification...

LessWrong (30+ Karma) ·

2024/10/08

How can we make many humans who are very good at solving difficult problems? Summary (table of made-up numbers) I made up the made-up numbers in this table of made-up numbers; therefore, the numbers in this table of made-up numbers are made-up numbers. Call to action If you have a shitload of money, there are some projects you can give money to that would make supergenius humans on demand happen faster. If you have a fuckton of money, there are projects whose creation you could fund that would

en-gb

4:58

“Evaluating the truth of statements in a world of...

LessWrong (30+ Karma) ·

2024/10/08

If I say "the store is 500 meters away," is this strictly true? Strictly false? Either strictly true or strictly false, with probabilies of true or false summing to one? Fuzzily true, because the store is 500.1 meters away? My thesis is that it's strictly true or strictly false, with associated probabilities. Bear with me. The 500 meter example is pretty hard to reason about numerically. I am hopeful that I can communicate my thoughts by starting with an example that is in some sense simpler. A

en-gb

16:51

“Advice for journalists” by Nathan Young

LessWrong (30+ Karma) ·

2024/10/08

I interact with journalists quite a lot and I have specific preferences. Not just for articles, but for behaviour. And journalists do behave pretty strangely at times. This account comes from talking to journalists on ~10 occasions. Including being quoted in ~5 articles. Privacy I do not trust journalists to abide by norms of privacy. If I talk to a friend and without asking, share what they said, with their name attached, I expect they'd be upset. But journalists regularly act as if their

en-gb

4:29

“Time Efficient Resistance Training” by romeostevensit

LessWrong (30+ Karma) ·

2024/10/08

Previously: https://www.lesswrong.com/posts/RydETq379eoWqBFvj/updates-and-reflections-on-optimal-exercise-after-nearly-ahttps://www.lesswrong.com/posts/bZ2w99pEAeAbKnKqo/optimal-exerciseI figured it would be useful to summarize how I train when I go for time efficiency these days, based on my understanding of the relevant meta-analyses on exercise selection and parameters. The primary time savers are supersets and lowered rest times. A routine like this is not totally optimized for max hypertrophy

en-gb

27:08

“MATS AI Safety Strategy Curriculum v2” by...

LessWrong (30+ Karma) ·

2024/10/08

As part of our Summer 2024 Program, MATS ran a series of discussion groups focused on questions and topics we believe are relevant to prioritizing research into AI safety. Each weekly session focused on one overarching question, and was accompanied by readings and suggested discussion questions. The purpose of running these discussions was to increase scholars’ knowledge about the AI safety ecosystem and models of how AI could cause a catastrophe, and hone scholars’ ability to think critically about

en-gb

47:04

“Research update: Towards a Law of Iterated...

LessWrong (30+ Karma) ·

2024/10/07

Audio note: this article contains 629 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Last week, ARC released a paper called Towards a Law of Iterated Expectations for Heuristic Estimators, which follows up on previous work on formalizing the presumption of independence. Most of the work described here was done in 2023.A brief table of contents for this post: What is a heuristic estimator? (One example and three

en-gb

21:15

“Toy Models of Feature Absorption in SAEs” by...

LessWrong (30+ Karma) ·

2024/10/07

TLDR;In previous work, we found a problematic form a feature splitting called "feature absorption" when analyzing Gemma Scope SAEs. We hypothesized that this was due to SAEs struggling to separate co-occurrence between features, but we did not prove this. In this post, we set up toy models where we can explicitly control feature representations and co-occurrence rates and show the following: Feature absorption happens when features co-occur.If co-occurring feature magnitudes vary relative to each

en-gb

8:07

“Compelling Villains and Coherent Values” by Cole Wyeth

LessWrong (30+ Karma) ·

2024/10/07

Epistemic status: This essay attempts to communicate intuitions strong shaped by @Joe Carlsmith's writing, particularly "On Green."Warning: very minor spoilers, mostly for "The Dark Knight".Some people have a sense of weight about them. They know exactly what they want and can explain why it is Right. Presented with a moral dilemma, they resolve conflicts between local values in a consistent way by appealing to higher values - they can tell you today whether they would actually pull the lever in the

en-gb

3:35

“A Narrow Path: a plan to deal with AI extinction...

LessWrong (30+ Karma) ·

2024/10/07

This is a link post.We have published A Narrow Path: our best attempt to draw out a comprehensive plan to deal with AI extinction risk. We propose concrete conditions that must be satisfied for addressing AI extinction risk, and offer policies that enforce these conditions.A Narrow Path answers the following: assuming extinction risk from AI, what would be a response that actually solves the problem for at least 20 years, and that leads to a stable global situation, one where the response is

en-gb

28:31

“(Maybe) A Bag of Heuristics is All There Is & A Bag...

LessWrong (30+ Karma) ·

2024/10/06

Epistemic status: Theorizing on topics I’m not qualified for. Trying my best to be truth-seeking instead of hyping up my idea. Not much here is original, but hopefully the combination is useful. This hypothesis deserves more time and consideration but I’m sharing this minimal version to get some feedback before sinking more time into it. “We believe there's a lot of value in articulating a strong version of something one may believe to be true, even if it might be false.” The Heuristics Hypothesis:

en-gb

3:15

“What is it like to be psychologically healthy?...

LessWrong (30+ Karma) ·

2024/10/06

Damon Sasi (@DaystarEld) is a mentor of mine, and he is also a therapist who claims to be very psychologically healthy. What's his inner experience like? “Probably for an average week, maybe I'll suffer for like five minutes”“I don't think I have any prolonged internal conflict”“Self-loathing to me was a weird concept […] Like, what does it mean to like self-loathe?” It's not that he had a great childhood, either.[My childhood] wasn't terrible. And I say this and then maybe I'll give some examples

en-gb

16:57

“ARENA4.0 Capstone: Hyperparameter tuning for MELBO +...

LessWrong (30+ Karma) ·

2024/10/06

Epistemic status: My coauthor and I are both noobs in this field. Expect errors and conceptual flaws. tl;drFor a four-day capstone project for the ARENA program my partner and I did a replication of the MELBO Lesswrong article using Llama-3.2-1b-Instruct. IntroI've been spending the last month at the ARENA program developing some basic technical skills to match my long-standing layman's interest in AI and AI X-risk. And ARENA's final week is a capstone project asking us to engage with current

en-gb

17:48

“Why I’m not a Bayesian” by Richard_Ngo

LessWrong (30+ Karma) ·

2024/10/06

This post focuses on philosophical objections to Bayesianism as an epistemology. I first explain Bayesianism and some standard objections to it, then lay out my two main objections (inspired by ideas in philosophy of science). A follow-up post will speculate about how to formalize an alternative. Degrees of beliefThe core idea of Bayesianism: we should ideally reason by assigning credences to propositions which represent our degrees of belief that those propositions are true.If that seems like a

en-gb

6:28

“AISafety.info: What is the ‘natural abstractions...

LessWrong (30+ Karma) ·

2024/10/06

IntroductionThe natural abstraction hypothesis (NAH) claims: Our physical world “abstracts well” into high-level abstractions of low-level systems.These abstractions are “natural” in the sense that many different kinds of learning processes acquire and use them.These abstractions approximately correspond to the concepts used by humans.If the NAH is true, AI alignment could be dramatically simplified, as it implies that any cognition a very powerful AI uses will be in terms of concepts that humans

en-gb

0:31

“If I have some money, whom should I donate it to in...

LessWrong (30+ Karma) ·

2024/10/04

I just want to make sure that when I donate money to AI alignment stuff it's actually going to be used economically ---First published: October 3rd, 2024 Source: https://www.lesswrong.com/posts/ryvtHuyo5CefieFsK/if-i-have-some-money-whom-should-i-donate-it-to-in-order-to --- Narrated by TYPE III AUDIO.

en-gb

52:35

“Information dark matter” by Logan Kieller

LessWrong (30+ Karma) ·

2024/10/04

I started collecting a list of once “secret” documents that were, in one way or another, broadly released (whether it be through legal process, government disclosures, leaks, or the ideas themselves eventually turned into books): Theanalysis done by Deutsche Bank investors to predict the 2008 financial crisis (dramatized as the Jenga scene from the movie “The Big Short”)Aconsulting project completed by BCG for the city of Dallas on their loose dog problemDeeplyinsightful tech emails surfaced through

en-gb

4:57

“The murderous shortcut: a toy model of instrumental...

LessWrong (30+ Karma) ·

2024/10/03

Suppose you can tell your AI to meet a certain spec (e.g. cure cancer), but most plans that meet the spec are unsafe (e.g. involve killing everyone, or so Rob Bensinger thinks). In these cases, a quantilizer is insufficient for safety due to instrumental convergence.[1]But suppose we can also give the agent a dispreference for unsafe actions like murder. In effect it has unsafe long-term goals but we control its immediate preferences.[2] When can we get the agent to cure cancer safely rather than

en-gb

51:26

“[Intuitive self-models] 3. The Homunculus” by Steven...

LessWrong (30+ Karma) ·

2024/10/02

3.1 Post summary / Table of contentsThis is the third of a series of eight blog posts, which I’m serializing over the next month or so. (Or email or DM me if you want to read the whole thing right now.)So far in the series, Post 1 established some foundations about intuitive self-models in general, and then Post 2 talked about the specific intuitive self-model concept “conscious awareness”.Now we’re ready to meet the protagonist starring in (most people's) intuitive self-models—the mental concept

en-gb

4:32

“Point of Failure: Semiconductor-Grade Quartz” by...

LessWrong (30+ Karma) ·

2024/10/02

This is a link post.ChatGPT 4o's interpretation of semiconductor grade quartzWe rarely think about where our stuff comes from or how it's made. We go through our lives expecting that the things we consume are easily acquired. That is the beauty of modern society: supply chain logistics work so well that we seldom think about the consequences if these systems are disrupted. I think many of us thought about this for the first time during the COVID-19 pandemic. It was a wake-up call that revealed how

en-gb

4:06

“Self-Help Corner: Loop Detection” by adamShimi

LessWrong (30+ Karma) ·

2024/10/02

This is a link post.The more I work on myself, the more I realize that the first step for me is almost always to just notice I’m stuck in a loop.As a teenager, I didn’t make progress towards getting good at anything because I was stuck in the following loop: Decide X is my passionGo all in for X, think about it all the time, redirect all my energy towards itAfter a variable amount of time (weeks, days, hours…), start worrying that I’m actually wrong, and that Y is actually much more representative,

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