PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

8:14

[Linkpost] “Things You’re Allowed to Do: University...

LessWrong (30+ Karma) ·

2024/02/06

This is a linkpost for https://www.brasstacks.blog/tyatd-uni/This post is not titled “Things You Should Do,” because these aren’t (necessarily) things you should do. Many people should not do many of the items on this list, and some of the items are exclusive, contradictory, or downright the reverse of what you should do. If your reaction to something is “I think that's a bad idea,” then it probably is, and you probably shouldn’t do it. classes & professors attend classes you haven’t signed up

en-gb

78:09

“Value learning in the absence of ground truth” by...

LessWrong (30+ Karma) ·

2024/02/05

Epistemic Status: My best guess.Summary. The problem of aligning AI is often phrased as the problem of aligning AI with human values, where “values” refers roughly to the normative considerations one leans upon in making decisions. Understood in this way, solving the problem would amount to first articulating the full set of human values that we want AI systems to learn, and then going about actually embedding these into the systems. However, it does not seem to be the case that there is a single

en-gb

11:20

“Implementing activation steering” by Annah

LessWrong (30+ Karma) ·

2024/02/05

Produced as part of the SERI ML Alignment Theory Scholars Program - Autumn 2023 Cohort and while being an affiliate at PIBBSS in 2024. A thank you to @Jayjay and @fela for helpful comments on this draft.This blog post is an overview of different ways to implement activation steering with some of my takes on their pros and cons. See also this GitHub repository for my minimal implementations of the different approaches.The blog post is aimed at people who are new to activation/representation

en-gb

2:13

“Safe Stasis Fallacy” by Davidmanheim

LessWrong (30+ Karma) ·

2024/02/05

A critical failure mode in many discussions of technological risk is the assumption that maintaining status quo for technology would lead to maintaining the status quo for society. Lewis Anslow suggests that this "propensity to treat technological stagnation as safer than technological acceleration" is a fallacy. I agree that it is an important failure of reasoning among some EAs, and want to call it out clearly. One obvious example of this, flagged by Anslow, is the anti-nuclear movement. It was

en-gb

5:23

“Noticing Panic” by Cole Wyeth

LessWrong (30+ Karma) ·

2024/02/05

In Competent Elites @Eliezer Yudkowsky discusses "executive nature," which he describes as the ability to "function without recourse," to make decisions without some higher decision maker to fall back on.I do not have executive nature. I like to be well prepared. I like to read every word of every chapter of a textbook before a problem set, take a look, give the last chapter another skim, and then start working. Being thrust into a new job and forced to explore a confusing repository and complete an

en-gb

9:13

“Brute Force Manufactured Consensus is Hiding the...

LessWrong (30+ Karma) ·

2024/02/03

People often parse information through an epistemic consensus filter. They do not ask "is this true", they ask "will others be OK with me thinking this is true". This makes them very malleable to brute force manufactured consensus; if every screen they look at says the same thing they will adopt that position because their brain interprets it as everyone in the tribe believing it.- Anon, 4Chan, slightly editedOrdinary people who haven't spent years of their lives thinking about rationality and

en-gb

7:14

“Theories of Applied Rationality” by Camille Berger

LessWrong (30+ Karma) ·

2024/02/03

tl;dr: within the LW community, there are many clusters of strategies to achieve rationality: doing basic exercices, using jargon, reading, partaking workshops, privileging object-level activities, and several other opinions like putting an accent on feedback loops, difficult conversations or altered states of consciousness. Epistemic status: This is a vague model to help me understand other rationalists and why some of them keep doing things I think are wrong, or suggest me to do things I think

en-gb

5:35

“Why I no longer identify as transhumanist” by...

LessWrong (30+ Karma) ·

2024/02/03

Someone asked me how come I used to have a strong identity as a singularitarian / transhumanist but don’t have it anymore. Here's what I answered them: ——- So I think the short version is something like: transhumanism/singularitarianism used to give me hope about things I felt strongly about. Molecular nanotechnology would bring material abundance, radical life extension would cure aging, AI would solve the rest of our problems. Over time, it started feeling like 1) not much was actually happening

en-gb

14:03

“Attention SAEs Scale to GPT-2 Small” by Connor...

LessWrong (30+ Karma) ·

2024/02/03

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is an interim report that we are currently building on. We hope this update + open sourcing our SAEs will be useful to related research occurring in parallel. Produced as part of the ML Alignment & Theory Scholars Program - Winter 2023-24 Cohort Executive Summary In a previous post, we showed thatsparse autoencoders (SAEs) work on the attention layer outputs of a two layer transformer. We scale our

en-gb

19:13

“Announcing the London Initiative for Safe AI (LISA)”...

LessWrong (30+ Karma) ·

2024/02/02

The LISA Team consists of James Fox, Mike Brozowski, Joe Murray, Nina Wolff-Ingham, Ryan Kidd, and Christian Smith.LISA's Advisory Board consists of Henry Sleight, Jessica Rumbelow, Marius Hobbhahn, Jamie Bernardi, and Callum McDougall.Everyone has contributed significantly to the founding of LISA, believes in its mission & vision, and assisted with writing this post. TL;DR: The London Initiative for Safe AI (LISA) is a new AI Safety research centre. Our mission is to improve the safety of

en-gb

1:30

“Survey for alignment researchers: help us build...

LessWrong (30+ Karma) ·

2024/02/02

AE Studio is launching a short, anonymous survey for alignment researchers, in order to develop a stronger model of various field-level dynamics in alignment. This appears to be an interestingly neglected research direction that we believe will yield specific and actionable insights related to the community's technical views and more general characteristics. The survey is a straightforward 5-10 minute Google Form with some simple multiple choice questions.For every alignment researcher who completes

en-gb

34:38

“On Dwarkesh’s 3rd Podcast With Tyler Cowen” by Zvi

LessWrong (30+ Karma) ·

2024/02/02

This post is extensive thoughts on Tyler Cowen's excellent talk with Dwarkesh Patel. It is interesting throughout. You can read this while listening, after listening or instead of listening, and is written to be compatible with all three options. The notes are in order in terms of what they are reacting to, and are mostly written as I listened. I see this as having been a few distinct intertwined conversations. Tyler Cowen knows more about more different things than perhaps anyone

en-gb

26:14

“Open Source Sparse Autoencoders for all Residual...

LessWrong (30+ Karma) ·

2024/02/02

This work was produced as part of the ML Alignment & Theory Scholars Program - Winter 2023-24 Cohort, under mentorship from Neel Nanda and Arthur Conmy. Funding for this work was provided by the Manifund Regranting Program and donors as well as LightSpeed Grants. This is intended to be a fairly informal post sharing a set of Sparse Autoencoders trained on the residual stream of GPT2-small which achieve fairly good reconstruction performance and contain fairly sparse / interpretable features

en-gb

7:35

[Linkpost] “Soft Prompts for Evaluation: Measuring...

LessWrong (30+ Karma) ·

2024/02/02

This is a linkpost for https://1drv.ms/b/s!AkbNRQZiRerJ60FS9KJ1qqIo9qyC?e=2AqBeH(The link above is likely going to expire in favor of arxiv once I get it submitted. Incidentally, if anyone wants to endorse me for cs.LG on arxiv, please DM me, and thanks!) Abstract:To help evaluate and understand the latent capabilities of language models, this paper introduces an approach using optimized input embeddings, or `soft prompts,' as a metric of conditional distance between a model and a target behavior

en-gb

2:15

[Linkpost] “Davidad’s Provably Safe AI Architecture -...

LessWrong (30+ Karma) ·

2024/02/01

This is a linkpost for https://www.aria.org.uk/wp-content/uploads/2024/01/ARIA-Safeguarded-AI-Programme-Thesis-V1.pdf The programme thesis of Davidad's agenda to develop provably safe AI has just been published. You can find extra details by downloading this doc. For context, Davidad is a Programme Director at ARIA who will grant somewhere between £10M and £50M over the next 3 years to pursue his research agenda. It is the most comprehensive public document detailing his agenda to date.Here's the

en-gb

2:17

“Wrong answer bias” by lukehmiles

LessWrong (30+ Karma) ·

2024/02/01

The correct answer leaves nothing to be said. The wrong answer starts a conversation, a research program, an investigation, a journey, an institute, a paper, a book, a youtube channel, a lifestyle, a tribe.Why is reading a textbook so boring? Very few people do it. It just has right answers and few great questions to ponder. Blogs arguing about nutrition are great reading though.If you write a research paper saying "all that shit is dumb just do the obvious thing" then you'll probably have trouble

en-gb

2:48

“On Not Requiring Vaccination” by jefftk

LessWrong (30+ Karma) ·

2024/02/01

A friend recently wrote that they wouldn't be attending a mask-optional contra dance weekend I'm playing at because it doesn't require vaccination. As an organizer of unrelated dance events, which also don't require vaccination, here's how I see the situation. When the covid vaccines first came out they were a huge improvement over the status quo. Getting the vaccine reduced your risk of severe illness or death, reduced your chance of catching it, and reduced your chance of giving it to

en-gb

3:10

“Managing risks while trying to do good” by Wei Dai

LessWrong (30+ Karma) ·

2024/02/01

I often think about "the road to hell is paved with good intentions".[1] I'm unsure to what degree this is true, but it does seem that people trying to do good have caused more negative consequences in aggregate than one might naively expect.[2] "Power corrupts" and "power-seekers using altruism as an excuse to gain power" are two often cited reasons for this, but I think don't explain all of it. A more subtle reason is that even when people are genuinely trying to do good, they're not entirely

en-gb

16:42

“Leading The Parade” by johnswentworth

LessWrong (30+ Karma) ·

2024/01/31

Background Terminology: Counterfactual Impact vs “Leading The Parade”Y’know how a parade or marching band has a person who walks in front waving a fancy-looking stick up and down? Like this guy:The classic 80's comedy Animal House features a great scene in which a prankster steals the stick, and then leads the marching band off the main road and down a dead-end alley.That is not the guy who's supposed to have that stick.In the context of the movie, it's hilarious. It's also, presumably, not at all

en-gb

2:53

“Per protocol analysis as medical malpractice” by braces

LessWrong (30+ Karma) ·

2024/01/31

“Per protocol analysis” is when medical trial researchers drop people who didn’t follow the treatment protocol. It is outrageous and must be stopped.For example: let's say you want to know the impact of daily jogs on happiness. You randomly instruct 80 people to either jog daily or to simply continue their regular routine. As a per protocol analyst, you drop the many treated people who did not go jogging. You keep the whole control group because it wasn’t as hard for them to follow instructions.At

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