LessWrong (Curated & Popular)

Latest Episodes:

"You can just spontaneously call people you haven't met in years" by lc Nov 17, 2023

Show notes

Here's a recent conversation I had with a friend:

Me: "I wish I had more friends. You guys are great, but I only get to hang out with you like once or twice a week. It's painful being holed up in my house the entire rest of the time."Friend: "You know ${X}. You could talk to him."Me: "I haven't talked to ${X} since 2019."Friend: "Why does that matter? Just call him."Me: "What do you mean 'just call him'? I can't do that."Friend: "Yes you can"Me:

Source:
https://www.lesswrong.com/posts/2HawAteFsnyhfYpuD/you-can-just-spontaneously-call-people-you-haven-t-met-in
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

[HUMAN VOICE] "AI Timelines" by habryka, Daniel Kokotajlo, Ajeya Cotra, Ege Erdil Nov 16, 2023

Show notes

Support ongoing human narrations of curated posts:
www.patreon.com/LWCurated
How many years will pass before transformative AI is built? Three people who have thought about this question a lot are Ajeya Cotra from Open Philanthropy, Daniel Kokotajlo from OpenAI and Ege Erdil from Epoch. Despite each spending at least hundreds of hours investigating this question, they still still disagree substantially about the relevant timescales. For instance, here are their median timelines for one operationalization of transformative AI:
Source:
https://www.lesswrong.com/posts/K2D45BNxnZjdpSX2j/ai-timelines
Narrated for LessWrong by Perrin Walker.
Share feedback on this narration.
[125+ Karma Post] ✓
[Curated Post] ✓

"EA orgs' legal structure inhibits risk taking and information sharing on the margin" by Elizabeth Nov 16, 2023

Show notes

It’s fairly common for EA orgs to provide fiscal sponsorship to other EA orgs. Wait, no, that sentence is not quite right. The more accurate sentence is that there are very few EA organizations, in the legal sense; most of what you think of as orgs are projects that are legally hosted by a single org, and which governments therefore consider to be one legal entity.
Source:
https://www.lesswrong.com/posts/XvEJydHAHk6hjWQr5/ea-orgs-legal-structure-inhibits-risk-taking-and-information
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"Integrity in AI Governance and Advocacy" by habryka, Olivia Jimenez Nov 16, 2023

Show notes

habryka

Ok, so we both had some feelings about the recent Conjecture post on "lots of people in AI Alignment are lying", and the associated marketing campaign and stuff.

I would appreciate some context in which I can think through that, and also to share info we have in the space that might help us figure out what's going on.

I expect this will pretty quickly cause us to end up on some broader questions about how to do advocacy, how much the current social network around AI Alignment should coordinate as a group, how to balance advocacy with research, etc.
Source:
https://www.lesswrong.com/posts/vFqa8DZCuhyrbSnyx/integrity-in-ai-governance-and-advocacy
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

Loudly Give Up, Don’t Quietly Fade Nov 16, 2023

Show notes

1.
There's a supercharged, dire wolf form of the bystander effect that I’d like to shine a spotlight on.
First, a quick recap. The Bystander Effect is a phenomenon where people are less likely to help when there's a group around. When I took basic medical training, I was told to always ask one specific person to take actions instead of asking a crowd at large. “You, in the green shirt! Call 911!” (911 is the emergency services number in the United States.) One habit I worked hard to instill in my own head was that if I’m in a crowd that's asked to do something, I silently count off three seconds. If nobody else responds, I either decide to do it or decide not to do it and I say that.
I like this habit, because the Bystander Effect is dumb and I want to fight it. Several [...]
---
First published:
November 13th, 2023
Source:
https://www.lesswrong.com/posts/bkfgTSHhm3mqxgTmw/loudly-give-up-don-t-quietly-fade
---
Narrated by TYPE III AUDIO.

[HUMAN VOICE] "Deception Chess: Game #1" by Zane et al. Nov 09, 2023

Show notes

Support ongoing human narrations of curated posts:
www.patreon.com/LWCurated
(You can sign up to play deception chess here if you haven't already.)

This is the first of my analyses of the deception chess games. The introduction will describe the setup of the game, and the conclusion will sum up what happened in general terms; the rest of the post will mostly be chess analysis and skippable if you just want the results. If you haven't read the original post, read it before reading this so that you know what's going on here.

The first game was between Alex A as player A, Chess.com computer Komodo 12 as player B, myself as the honest C advisor, and aphyer and AdamYedidia as the deceptive Cs. (Someone else randomized the roles for the Cs and told us in private.)
Source:
https://www.lesswrong.com/posts/6dn6hnFRgqqWJbwk9/deception-chess-game-1
Narrated for LessWrong by Perrin Walker.
Share feedback on this narration.
[125+ Karma Post] ✓
[Curated Post] ✓

[HUMAN VOICE] "Towards Monosemanticity: Decomposing Language Models With Dictionary Learning" by Zac Hatfield-Dodds Nov 09, 2023

Show notes

Support ongoing human narrations of curated posts:
www.patreon.com/LWCurated
This is a linkpost for https://transformer-circuits.pub/2023/monosemantic-features/

Text of post based on our blog post as a linkpost for the full paper which is considerably longer and more detailed.

Neural networks are trained on data, not programmed to follow rules. We understand the math of the trained network exactly – each neuron in a neural network performs simple arithmetic – but we don't understand why those mathematical operations result in the behaviors we see. This makes it hard to diagnose failure modes, hard to know how to fix them, and hard to certify that a model is truly safe.

Luckily for those of us trying to understand artificial neural networks, we can simultaneously record the activation of every neuron in the network, intervene by silencing or stimulating them, and test the network's response to any possible input.

Unfortunately, it turns out that the individual neurons do not have consistent relationships to network behavior. For example, a single neuron in a small language model is active in many unrelated contexts, including: academic citations, English dialogue, HTTP requests, and Korean text. In a classic vision model, a single neuron responds to faces of cats and fronts of cars. The activation of one neuron can mean different things in different contexts.
Source:
https://www.lesswrong.com/posts/TDqvQFks6TWutJEKu/towards-monosemanticity-decomposing-language-models-with
Narrated for LessWrong by Perrin Walker.
Share feedback on this narration.
[125+ Karma Post] ✓
[Curated Post] ✓

"The 6D effect: When companies take risks, one email can be very powerful." by scasper Nov 09, 2023

Show notes

Recently, I have been learning about industry norms, legal discovery proceedings, and incentive structures related to companies building risky systems. I wanted to share some findings in this post because they may be important for the frontier AI community to understand well.

TL;DR

Documented communications of risks (especially by employees) make companies much more likely to be held liable in court when bad things happen. The resulting Duty to Due Diligence from Discoverable Documentation of Dangers (the 6D effect) can make companies much more cautious if even a single email is sent to them communicating a risk.
Source:
https://www.lesswrong.com/posts/J9eF4nA6wJW6hPueN/the-6d-effect-when-companies-take-risks-one-email-can-be
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"The other side of the tidal wave" by Katja Grace Nov 09, 2023

Show notes

I guess there’s maybe a 10-20% chance of AI causing human extinction in the coming decades, but I feel more distressed about it than even that suggests—I think because in the case where it doesn’t cause human extinction, I find it hard to imagine life not going kind of off the rails. So many things I like about the world seem likely to be over or badly disrupted with superhuman AI (writing, explaining things to people, friendships where you can be of any use to one another, taking pride in skills, thinking, learning, figuring out how to achieve things, making things, easy tracking of what is and isn’t conscious), and I don’t trust that the replacements will be actually good, or good for us, or that anything will be reversible.

Even if we don’t die, it still feels like everything is coming to an end.
Source:
https://www.lesswrong.com/posts/uyPo8pfEtBffyPdxf/the-other-side-of-the-tidal-wave
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"Does davidad's uploading moonshot work?" by jacobjabob et al. Nov 09, 2023

Show notes

davidad has a 10-min talk out on a proposal about which he says: “the first time I’ve seen a concrete plan that might work to get human uploads before 2040, maybe even faster, given unlimited funding”.

I think the talk is a good watch, but the dialogue below is pretty readable even if you haven't seen it. I'm also putting some summary notes from the talk in the Appendix of this dialogue.
Source:
https://www.lesswrong.com/posts/FEFQSGLhJFpqmEhgi/does-davidad-s-uploading-moonshot-work
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

Our TOPPODCAST Picks

Follow Us

Stay Connected

LessWrong (Curated & Popular)

Related Podcasts

Links

Stay Connected