x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

LessWrong (Curated & Popular)

Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma.If you"d like more, subscribe to the “Lesswrong (30+ karma)” feed.

technology philosophy

All Episodes

5:12

“Maybe Anthropic’s Long-Term Benefit Trust is...

LessWrong (Curated & Popular) ·

2024/05/28

Crossposted from AI Lab Watch. Subscribe on Substack.Introduction. Anthropic has an unconventional governance mechanism: an independent "Long-Term Benefit Trust" elects some of its board. Anthropic sometimes emphasizes that the Trust is an experiment, but mostly points to it to argue that Anthropic will be able to promote safety and benefit-sharing over profit.[1]But the Trust's details have not been published and some information Anthropic has shared is concerning. In particular, ...

en

16:07

“Notifications Received in 30 Minutes of Class” by...

LessWrong (Curated & Popular) ·

2024/05/27

Introduction. If you are choosing to read this post, you've probably seen the image below depicting all the notifications students received on their phones during one class period. You probably saw it as a retweet of this tweet, or in one of Zvi's posts. Did you find this data plausible, or did you roll to disbelieve? Did you know that the image dates back to at least 2019? Does that fact make you more or less worried about the truth on the ground as of 2024?Last month, I performed...

en

7:42

AI companies aren’t really using external evaluators

LessWrong (Curated & Popular) ·

2024/05/24

New blog: AI Lab Watch. Subscribe on Substack.Many AI safety folks think that METR is close to the labs, with ongoing relationships that grant it access to models before they are deployed. This is incorrect. METR (then called ARC Evals) did pre-deployment evaluation for GPT-4 and Claude 2 in the first half of 2023, but it seems to have had no special access since then.[1] Other model evaluators also seem to have little access before deployment.Frontier AI labs' pre-deployment risk assessment ...

en

6:42

EIS XIII: Reflections on Anthropic’s SAE Research...

LessWrong (Curated & Popular) ·

2024/05/24

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.Part 13 of 12 in the Engineer's Interpretability Sequence. TL;DROn May 5, 2024, I made a set of 10 predictions about what the next sparse autoencoder (SAE) paper from Anthropic would and wouldn’t do. Today's new SAE paper from Anthropic was full of brilliant experiments and interesting insights, but it ultimately underperformed my expectations. I am beginning to be concerned that Anthropic's recent approach ...

en

6:30

What’s Going on With OpenAI’s Messaging?

LessWrong (Curated & Popular) ·

2024/05/22

This is a quickly-written opinion piece, of what I understand about OpenAI. I first posted it to Facebook, where it had some discussion. Some arguments that OpenAI is making, simultaneously: OpenAI will likely reach and own transformative AI (useful for attracting talent to work there). OpenAI cares a lot about safety (good for public PR and government regulations). OpenAI isn’t making anything dangerous and is unlikely to do so in the future (good for public PR and government regulation...

en

29:05

Language Models Model Us

LessWrong (Curated & Popular) ·

2024/05/21

Produced as part of the MATS Winter 2023-4 program, under the mentorship of @Jessica RumbelowOne-sentence summary: On a dataset of human-written essays, we find that gpt-3.5-turbo can accurately infer demographic information about the authors from just the essay text, and suspect it's inferring much more. Introduction. Every time we sit down in front of an LLM like GPT-4, it starts with a blank slate. It knows nothing[1] about who we are, other than what it knows about users in general. But ...

en

0:51

Jaan Tallinn’s 2023 Philanthropy Overview

LessWrong (Curated & Popular) ·

2024/05/21

This is a link post.to follow up my philantropic pledge from 2020, i've updated my philanthropy page with 2023 results.in 2023 my donations funded $44M worth of endpoint grants ($43.2M excluding software development and admin costs) — exceeding my commitment of $23.8M (20k times $1190.03 — the minimum price of ETH in 2023).--- First published: May 20th, 2024 Source: https://www.lesswrong.com/posts/bjqDQB92iBCahXTAj/jaan-tallinn-s-2023-philanthropy-over...

en

84:44

OpenAI: Exodus

LessWrong (Curated & Popular) ·

2024/05/21

Previously: OpenAI: Facts From a Weekend, OpenAI: The Battle of the Board, OpenAI: Leaks Confirm the Story, OpenAI: Altman Returns, OpenAI: The Board Expands.Ilya Sutskever and Jan Leike have left OpenAI. This is almost exactly six months after Altman's temporary firing and The Battle of the Board, the day after the release of GPT-4o, and soon after a number of other recent safety-related OpenAI departures. Many others working on safety have also left recently. This is part of a longstanding ...

en

7:20

DeepMind’s ”Frontier Safety Framework” is weak and...

LessWrong (Curated & Popular) ·

2024/05/20

FSF blogpost. Full document (just 6 pages; you should read it). Compare to Anthropic's RSP, OpenAI's RSP ("PF"), and METR's Key Components of an RSP.DeepMind's FSF has three steps: Create model evals for warning signs of "Critical Capability Levels" Evals should have a "safety buffer" of at least 6x effective compute so that CCLs will not be reached between evalsThey list 7 CCLs across "Autonomy, Biosecurity, Cybersecurity, and Machine Learning R&D" E.g. "Autonomy level 1: Capable of expa...

en

11:29

Do you believe in hundred dollar bills lying on the...

LessWrong (Curated & Popular) ·

2024/05/18

Introduction. [Reminder: I am an internet weirdo with no medical credentials]A few months ago, I published some crude estimates of the power of nitric oxide nasal spray to hasten recovery from illness, and speculated about what it could do prophylactically. While working on that piece a nice man on Twitter alerted me to the fact that humming produces lots of nasal nitric oxide. This post is my very crude model of what kind of anti-viral gains we could expect from humming.I’ve encoded my mode...

en

15:22

Deep Honesty

LessWrong (Curated & Popular) ·

2024/05/12

Most people avoid saying literally false things, especially if those could be audited, like making up facts or credentials. The reasons for this are both moral and pragmatic — being caught out looks really bad, and sustaining lies is quite hard, especially over time. Let's call the habit of not saying things you know to be false ‘shallow honesty’[1].Often when people are shallowly honest, they still choose what true things they say in a kind of locally act-consequentialist way, to try to brin...

en

14:29

On Not Pulling The Ladder Up Behind You

LessWrong (Curated & Popular) ·

2024/05/02

Epistemic Status: Musing and speculation, but I think there's a real thing here. 1.When I was a kid, a friend of mine had a tree fort. If you've never seen such a fort, imagine a series of wooden boards secured to a tree, creating a platform about fifteen feet off the ground where you can sit or stand and walk around the tree. This one had a rope ladder we used to get up and down, a length of knotted rope that was tied to the tree at the top and dangled over the edge so that it reached the gr...

en

80:59

Mechanistically Eliciting Latent Behaviors in...

LessWrong (Curated & Popular) ·

2024/05/02

Produced as part of the MATS Winter 2024 program, under the mentorship of Alex Turner (TurnTrout).TL,DR: I introduce a method for eliciting latent behaviors in language models by learning unsupervised perturbations of an early layer of an LLM. These perturbations are trained to maximize changes in downstream activations. The method discovers diverse and meaningful behaviors with just one prompt, including perturbations overriding safety training, eliciting backdoored behaviors and uncovering ...

en

18:59

Ironing Out the Squiggles

LessWrong (Curated & Popular) ·

2024/05/01

Adversarial Examples: A ProblemThe apparent successes of the deep learning revolution conceal a dark underbelly. It may seem that we now know how to get computers to (say) check whether a photo is of a bird, but this façade of seemingly good performance is belied by the existence of adversarial examples—specially prepared data that looks ordinary to humans, but is seen radically differently by machine learning models.The differentiable nature of neural networks, which make them possible to b...

en

2:42

Introducing AI Lab Watch

LessWrong (Curated & Popular) ·

2024/05/01

This is a linkpost for https://ailabwatch.orgI'm launching AI Lab Watch. I collected actions for frontier AI labs to improve AI safety, then evaluated some frontier labs accordingly.It's a collection of information on what labs should do and what labs are doing. It also has some adjacent resources, including a list of other safety-ish scorecard-ish stuff.(It's much better on desktop than mobile — don't read it on mobile.)It's in beta—leave feedback here or comment or DM me—but I basically end...

en

17:07

Refusal in LLMs is mediated by a single direction

LessWrong (Curated & Popular) ·

2024/04/28

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This work was produced as part of Neel Nanda's stream in the ML Alignment & Theory Scholars Program - Winter 2023-24 Cohort, with co-supervision from Wes Gurnee.This post is a preview for our upcoming paper, which will provide more detail into our current understanding of refusal.We thank Nina Rimsky and Daniel Paleka for the helpful conversations and review. Executive summaryModern LLMs are typically fi...

en

4:06

Funny Anecdote of Eliezer From His Sister

LessWrong (Curated & Popular) ·

2024/04/24

This comes from a podcast called 18Forty, of which the main demographic of Orthodox Jews. Eliezer's sister (Hannah) came on and talked about her Sheva Brachos, which is essentially the marriage ceremony in Orthodox Judaism. People here have likely not seen it, and I thought it was quite funny, so here it is: https://18forty.org/podcast/channah-cohen-the-crisis-of-experience/David Bashevkin:So I want to shift now and I want to talk about something that full disclosure, we recorded this once be...

en

34:23

Thoughts on seed oil

LessWrong (Curated & Popular) ·

2024/04/21

This is a linkpost for https://dynomight.net/seed-oil/A friend has spent the last three years hounding me about seed oils. Every time I thought I was safe, he’d wait a couple months and renew his attack:“When are you going to write about seed oils?”“Did you know that seed oils are why there's so much {obesity, heart disease, diabetes, inflammation, cancer, dementia}?”“Why did you write about {meth, the death penalty, consciousness, nukes, ethylene, abortion, AI, aliens, colonoscopies, Tunnel ...

en

12:36

Why Would Belief-States Have A Fractal Structure, And...

LessWrong (Curated & Popular) ·

2024/04/19

Yesterday Adam Shai put up a cool post which… well, take a look at the visual:Yup, it sure looks like that fractal is very noisily embedded in the residual activations of a neural net trained on a toy problem. Linearly embedded, no less.I (John) initially misunderstood what was going on in that post, but some back-and-forth with Adam convinced me that it really is as cool as that visual makes it look, and arguably even cooler. So David and I wrote up this post / some code, partly as an explai...

en

5:44

Express interest in an “FHI of the West”

LessWrong (Curated & Popular) ·

2024/04/18

TLDR: I am investigating whether to found a spiritual successor to FHI, housed under Lightcone Infrastructure, providing a rich cultural environment and financial support to researchers and entrepreneurs in the intellectual tradition of the Future of Humanity Institute. Fill out this form or comment below to express interest in being involved either as a researcher, entrepreneurial founder-type, or funder.The Future of Humanity Institute is dead:I knew that this was going to happen in some fo...

en

601 results

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs