PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

5:27

“Misnaming and Other Issues with OpenAI’s ‘Human...

LessWrong (30+ Karma) ·

2024/07/15

Bloomberg reports that OpenAI internally has benchmarks for “Human-Level AI.” They have 5 levels, with the first being the achieved level of having intelligent conversation, to level 2, “[unassisted, PhD-level] Reasoners,” level 3, “Agents,” level 4, systems that can “come up with new innovations,” and finally level 5, “AI that can do the work of… Organizations.” The levels, in brief, are:1 - Conversation 2 - Reasoning 3 - Agent 4 - Innovation 5 - Organization This is being reported secondhand,

en-gb

2:06

“Breaking Circuit Breakers” by mikes, tbenthompson

LessWrong (30+ Karma) ·

2024/07/15

This is a link post.A few days ago, Gray Swan published code and models for their recent “circuit breakers” method for language models.[1]1The circuit breakers method defends against jailbreaks by training the model to erase “bad” internal representations. We are very excited about data-efficient defensive methods like this, especially those which use interpretability concepts or tools.At the link, we briefly investigate three topics: Increased refusal rates on harmless prompts: Do circuit breakers

en-gb

2:38

“Whiteboard Pen Magazines are Useful” by Johannes C....

LessWrong (30+ Karma) ·

2024/07/15

Glue your colored whiteboard makers together with duck tape to create a whiteboard pen magazine. If required glue a paper layer around the duck tape to make it non-sticky to the touch. Mark which side is up with an arrow, such that you can always <hold it/pick it up> in the same way.This more than doubled my color-switching speed, fits in my pocket, and takes <5m to make. It lasts: When a pen is empty just insert a new one. No need to create another magazine. No signs of degradation after

en-gb

4:08

“LLMs as a Planning Overhang” by Larks

LessWrong (30+ Karma) ·

2024/07/14

It's quite possible someone has already argued this, but I thought I should share just in case not. Goal-Optimisers and Planner-SimulatorsWhen people in the past discussed worries about AI development, this was often about AI agents - AIs that had goals they were attempting to achieve, objective functions they were trying to maximise. At the beginning we would make fairly low-intelligence agents, which were not very good at achieving things, and then over time we would make them more and more

en-gb

0:39

“Ice: The Penultimate Frontier” by Roko

LessWrong (30+ Karma) ·

2024/07/14

This is a link post.I argue here that preventing a large iceberg from melting is absurdly cheap per unit area compared to just about any other way of making new land, and it's kind of crazy to spend money on space exploration and colonization before colonizing the oceans with floating ice-islands. --- First published: July 13th, 2024 Source: https://www.lesswrong.com/posts/gthjxPDywrMTs3p2j/ice-the-penultimate-frontier --- Narrated by

en-gb

8:11

“Brief notes on the Wikipedia game” by Olli Järviniemi

LessWrong (30+ Karma) ·

2024/07/14

Alex Turner introduced an exercise to test subjects’ ability to notice falsehoods: change factual statements in Wikipedia articles, hand the edited articles to subjects and see whether they notice the modifications.I’ve spent a few hours making such modifications and testing the articles on my friend group. You can find the articles here. I describe my observations and thoughts below. The bottom line: it is hard to come up with good modifications / articles to modify, and this is the biggest crux

en-gb

14:10

“A simple case for extreme inner misalignment” by...

LessWrong (30+ Karma) ·

2024/07/13

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This post is the version of Yudkowsky's argument for inner misalignment that I wish I'd had in my head a few years ago. I don't claim that it's novel, that I endorse it, or even that Yudkowsky would endorse it; it's primarily an attempt to map his ideas into an ontology that makes sense to me (and hopefully others).This post is formulated in terms of three premises, which I explore in turn. My arguments

en-gb

80:08

“Robin Hanson AI X-Risk Debate — Highlights and...

LessWrong (30+ Karma) ·

2024/07/13

This is a link post.This linkpost contains a lightly-edited transcript of highlights of my recent AI x-risk debate with Robin Hanson, and a written version of what I said in the post-debate analysis episode of my Doom Debates podcast. IntroductionI've poured over my recent 2-hour AI x-risk debate with Robin Hanson to clip the highlights and write up a post-debate analysis, including new arguments I thought of after the debate was over.I've read everybody's feedback on YouTube and Twitter, and the

en-gb

8:26

“Sherlockian Abduction Master List” by Cole Wyeth

LessWrong (30+ Karma) ·

2024/07/13

Epistemic status: Mostly speculation and anecdotes, feel free to skip to The List once you understand its reason for existence.tldr: This is a curated list of observable details about a person's appearance that indicate something useful/surprising about them. Ideally, studying this list will be an efficient way to cultivate more insightful observational/abductive abilities, approaching the fictional example of Sherlock Holmes. Please contribute in the comments section after reading the

en-gb

5:28

“Timaeus is hiring!” by Jesse Hoogland, Stan van...

LessWrong (30+ Karma) ·

2024/07/13

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.TLDR: We’re hiring two research assistants to work on advancing developmental interpretability and other applications of singular learning theory to alignment. About UsTimaeus's mission is to empower humanity by making breakthrough scientific progress on alignment. Our research focuses on applications of singular learning theory to foundational problems within alignment, such as interpretability (via

en-gb

76:12

“AI #72: Denying the Future” by Zvi

LessWrong (30+ Karma) ·

2024/07/12

The Future. It is coming.A surprising number of economists deny this when it comes to AI. Not only do they deny the future that lies in the future. They also deny the future that is here, but which is unevenly distributed. Their predictions and projections do not factor in even what the AI can already do, let alone what it will learn to do later on. Another likely future event is the repeal of the Biden Executive Order. That repeal is part of the Republican platform, and Trump is the

en-gb

28:22

“Most smart and skilled people are outside of the...

LessWrong (30+ Karma) ·

2024/07/12

This is a link post. Introduction: The (highly interrelated) effective altruist and Rationalist communities are very small on a global scale. Therefore, in general, most intelligence, skill and expertise is outside of the community, not within it. I don’t think many people will disagree with this statement. But sometimes it's worth reminding people of the obvious, and also it is worth quantifying and visualizing the obvious, to get a proper feel for the scale of the difference. I think some people

en-gb

15:03

“Transformer Circuit Faithfulness Metrics Are Not...

LessWrong (30+ Karma) ·

2024/07/12

This is a link post.When you think you've found a circuit in a language model, how do you know if it does what you think it does? Typically, you ablate / resample the activations of the model in order to isolate the circuit. Then you measure if the model can still perform the task you're investigating.We identify six ways in which ablation experiments often vary.[1][2]How do these variations change the results of experiments that measure circuit faithfulness? TL;DR We study three different circuits

en-gb

19:10

“Superbabies: Putting The Pieces Together” by...

LessWrong (30+ Karma) ·

2024/07/12

This post was inspired by some talks at the recent LessOnline conference including one by LessWrong user “Gene Smith”.Let's say you want to have a “designer baby”. Genetically extraordinary in some way — super athletic, super beautiful, whatever.6’5”, blue eyes, with a trust fund.Ethics aside[1], what would be necessary to actually do this?Fundamentally, any kind of “superbaby” or “designer baby” project depends on two steps:1.) figure out what genes you ideally want;2.) create an embryo with those

en-gb

19:10

“Superbabies: Putting The Pieces Together” by...

LessWrong (30+ Karma) ·

2024/07/12

en-gb

2:07

“Yoshua Bengio: Reasoning through arguments against...

LessWrong (30+ Karma) ·

2024/07/12

This is a link post.He starts by emphasizingThe issue is so hotly debated because the stakes are major: According to some estimates, quadrillions of dollars of net present value are up for grabs, not to mention political power great enough to significantly disrupt the current world order.[...]The most important thing to realize, through all the noise of discussions and debates, is a very simple and indisputable fact: while we are racing towards AGI or even ASI, nobody currently knows how such an AGI

en-gb

24:04

“Decomposing Agency — capabilities without desires”...

LessWrong (30+ Karma) ·

2024/07/11

This is a link post.What is an agent? It's a slippery concept with no commonly accepted formal definition, but informally the concept seems to be useful. One angle on it is Dennet's Intentional Stance: we think of an entity as being an agent if we can more easily predict it by treating it as having some beliefs and desires which guide its actions. Examples include cats and countries, but the central case is humans.The world is shaped significantly by the choices agents make. What might agents look

en-gb

24:13

“Decomposing Agency — capabilities without desires”...

LessWrong (30+ Karma) ·

2024/07/11

This is a link post.What is an agent? It's a slippery concept with no commonly accepted formal definition, but informally the concept seems to be useful. One angle on it is Dennett's Intentional Stance: we think of an entity as being an agent if we can more easily predict it by treating it as having some beliefs and desires which guide its actions. Examples include cats and countries, but the central case is humans.The world is shaped significantly by the choices agents make. What might agents look

en-gb

0:43

“UC Berkeley course on LLMs and ML Safety” by Dan H

LessWrong (30+ Karma) ·

2024/07/11

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.The UC Berkeley course I co-taught now has lecture videos available: https://www.youtube.com/playlist?list=PLJ66BAXN6D8H_gRQJGjmbnS5qCWoxJNfeCourse site: Understanding LLMs: Foundations and SafetyUnrelatedly, a more conceptual AI safety course has its content available at https://www.aisafetybook.com/ ---First published: July 9th, 2024 Source:

en-gb

2:38

“[EAForum xpost] A breakdown of OpenAI’s revenue” by...

LessWrong (30+ Karma) ·

2024/07/10

This is a link post.We estimate that, as of June 12, 2024, OpenAI has an annualized revenue (ARR) of: $1.9B for ChatGPT Plus (7.7M global subscribers), $714M from ChatGPT Enterprise (1.2M seats), $510M from the API, and $290M from ChatGPT Team (from 980k seats)(Full report in https://app.futuresearch.ai/reports/3Li1, methods described in https://futuresearch.ai/openai-revenue-report.) We looked into OpenAI's revenue because financial information should be a strong indicator of the business

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