PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

62:41

“What’s up with all the non-Mormons? Weirdly specific...

LessWrong (30+ Karma) ·

2024/04/20

tl;dr: Recently reported GPT-J experiments [1 2 3 4] prompting for definitions of points in the so-called "semantic void" (token-free regions of embedding space) were extended to fifteen other open source base models from four families, producing many of the same bafflingly specific outputs. This points to an entirely unexpected kind of LLM universality (for which no explanation is offered, although a few highly speculative ideas are riffed upon).Work supported by the Long Term Future Fund. Thanks

en-gb

34:23

[Linkpost] “Thoughts on seed oil” by dynomight

LessWrong (30+ Karma) ·

2024/04/20

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 Man,

en-gb

28:08

“Inducing Unprompted Misalignment in LLMs” by Sam...

LessWrong (30+ Karma) ·

2024/04/20

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Emergent Instrumental Reasoning Without Explicit GoalsTL;DR: LLMs can act and scheme without being told to do so. This is bad. Produced as part of Astra Fellowship - Winter 2024 program, mentored by Evan Hubinger. Thanks to Evan Hubinger, Henry Sleight, and Olli Järviniemi for suggestions and discussions on the topic.Introduction. Skeptics of deceptive alignment argue that current language models do not

en-gb

2:45

[Linkpost] “Daniel Dennett has died (1924-2024)” by kave

LessWrong (30+ Karma) ·

2024/04/19

This is a linkpost for https://dailynous.com/2024/04/19/daniel-dennett-death-1942-2024/Daniel Dennett, professor emeritus of philosophy at Tufts University, well-known for his work in philosophy of mind and a wide range of other philosophical areas, has died.Professor Dennett wrote extensively about issues related to philosophy of mind and cognitive science, especially consciousness. He is also recognized as having made significant contributions to the concept of intentionality and debates on free

en-gb

4:49

“Experiment on repeating choices” by KatjaGrace

LessWrong (30+ Karma) ·

2024/04/19

People behave differently from one another on all manner of axes, and each person is usually pretty consistent about it. For instance:how much to spend money how much to worry how much to listen vs. speak how much to jump to conclusions how much to work how playful to be how spontaneous to be how much to prepare How much to socialize How much to exercise How much to smile how honest to be How snarky to be How to trade off convenience, enjoyment, time and healthiness in food These are often

en-gb

8:03

“[Fiction] A Confession” by Arjun Panickssery

LessWrong (30+ Karma) ·

2024/04/19

This morning while taking the LIRR to the city I performed first aid on a man who had been shot through the window of my carriage.“Is he going to die?” his girlfriend asked me.“We’re all going to die.”A long pause. “I mean—is he going to die right now?”“Probably not.” Probably he didn’t die. I got off at Jamaica Station while he stayed on (he was unconscious) so I don’t know. I didn’t want to be questioned at length as a witness since it was my day off.I continued toward a barbershop I like. There

en-gb

1:42

“I’m open for projects (sort of)” by cousin_it

LessWrong (30+ Karma) ·

2024/04/18

I left Google a month ago and right now don't work. Writing this post in case anyone has interesting ideas what I could do. This isn't an "urgently need help" kind of thing - I have a little bit of savings, right now planning to relax some more weeks and then go into some solo software work. But I thought I'd write this here anyway, because who knows what'll come up.Some things about me. My degree many years ago was in math. My software credentials are okayish: I left Google at L5, worked at many

en-gb

116:11

“AI #60: Oh the Humanity” by Zvi

LessWrong (30+ Karma) ·

2024/04/18

Many things this week did not go as planned. Humane AI premiered its AI pin. Reviewers noticed it was, at best, not ready. Devin turns out to have not been entirely forthright with its demos. OpenAI fired two employees who had been on its superalignment team, Leopold Aschenbrenner and Pavel Izmailov for allegedly leaking information, and also more troubliningly lost Daniel Kokotajlo, who expects AGI very soon, does not expect it to by default go well, and says he quit ‘due to losing

en-gb

25:46

“Discriminating Behaviorally Identical Classifiers: a...

LessWrong (30+ Karma) ·

2024/04/18

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.In a new preprint, Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models, my coauthors and I introduce a technique, Sparse Human-Interpretable Feature Trimming (SHIFT), which I think is the strongest proof-of-concept yet for applying AI interpretability to existential risk reduction.[1] In this post, I will explain how SHIFT fits into a broader agenda for what I call

en-gb

20:25

“The Mom Test: Summary and Thoughts” by Adam Zerner

LessWrong (30+ Karma) ·

2024/04/18

I just finished reading The Mom Test for the second time. I took raw notes here. In this post I'll first write up a bullet-point summary and then ramble off some thoughts that I have.Summary. Introduction: Trying to learn from customer conversations is like trying to excavate a delicate archeological site. The truth is down there somewhere, but it's fragile. When you dig you get closer to the truth, but you also risk damaging or smashing it.Bad customer conversations are worse than useless because

en-gb

48:42

“Childhood and Education Roundup #5” by Zvi

LessWrong (30+ Karma) ·

2024/04/18

For this iteration I will exclude discussions involving college or college admissions. There has been a lot of that since the last time I did one of these, along with much that I need to be careful with lest I go out of my intended scope. It makes sense to do that as its own treatment another day. Bullying Why do those who defend themselves against bullies so often get in more trouble than bullies? This is also true in other contexts but especially true in school. Thread is extensive,

en-gb

1:39

[Linkpost] “Claude 3 Opus can operate as a Turing...

LessWrong (30+ Karma) ·

2024/04/18

This is a linkpost for https://twitter.com/ctjlewis/status/1779740038852690393Posted on Twitter: Opus can operate as a Turing machine.given only existing tapes, it learns the rules and computes new sequences correctly.100% accurate over 500+ 24-step solutions (more tests running).for 100% at 24 steps, the input tapes weigh 30k tokens*.GPT-4 cannot do this.Here is the prompt code for the Turing machine: https://github.com/SpellcraftAI/turing This is the fully general counterpoint to the

en-gb

5:45

“Express interest in an ‘FHI of the West’” by habryka

LessWrong (30+ Karma) ·

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 form or

en-gb

12:36

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

LessWrong (30+ Karma) ·

2024/04/18

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 explainer for

en-gb

14:09

“Effectively Handling Disagreements - Introducing a...

LessWrong (30+ Karma) ·

2024/04/17

On May 25th, 2023, someone posted a review of How Minds Change on LessWrong. It talked about Street Epistemology, Deep Canvassing, and Smart Politics, ways of handling disagreements that open the possibility of rational belief progression through amicable discussions. Summarized quickly, they rely on active listening, sharing personal stories and socratic questioning.You can now learn all of those three techniques online, for free, in 4 hours, and in a Deliberate Practice setting. If interested, you

en-gb

4:41

[Linkpost] “Moving on from community living” by Vika

LessWrong (30+ Karma) ·

2024/04/17

This is a linkpost for https://vkrakovna.wordpress.com/2024/04/17/moving-on-from-community-living/After 7 years at Deep End (and 4 more years in other group houses before that), Janos and I have moved out to live near a school we like and some lovely parks. The life change is bittersweet - we will miss living with our friends, but also look forward to a logistically simpler life with our kids. Looking back, here are some thoughts on what worked and didn't work well about living in a group house with

en-gb

0:27

[Linkpost] “FHI (Future of Humanity Institute) has...

LessWrong (30+ Karma) ·

2024/04/17

This is a linkpost for https://www.futureofhumanityinstitute.org/ ---First published: April 17th, 2024 Source: https://www.lesswrong.com/posts/tu3CH22nFLLKouMKw/fhi-future-of-humanity-institute-has-shut-down-2005-2024 Linkpost URL:https://www.futureofhumanityinstitute.org/ --- Narrated by TYPE III AUDIO.

en-gb

26:23

“When is a mind me?” by Rob Bensinger

LessWrong (30+ Karma) ·

2024/04/17

xlr8harder writes:In general I don’t think an uploaded mind is you, but rather a copy. But one thought experiment makes me question this. A Ship of Theseus concept where individual neurons are replaced one at a time with a nanotechnological functional equivalent.Are you still you?Presumably the question xlr8harder cares about here isn't semantic question of how linguistic communities use the word "you", or predictions about how whole-brain emulation tech might change the way we use pronouns.Rather,

en-gb

2:56

“Mid-conditional love” by KatjaGrace

LessWrong (30+ Karma) ·

2024/04/17

People talk about unconditional love and conditional love. Maybe I’m out of the loop regarding the great loves going on around me, but my guess is that love is extremely rarely unconditional. Or at least if it is, then it is either very broadly applied or somewhat confused or strange: if you love me unconditionally, presumably you love everything else as well, since it is only conditions that separate me from the worms.I do have sympathy for this resolution—loving someone so unconditionally that

en-gb

23:52

“Transformers Represent Belief State Geometry in...

LessWrong (30+ Karma) ·

2024/04/16

Produced while being an affiliate at PIBBSS[1]. The work was done initially with funding from a Lightspeed Grant, and then continued while at PIBBSS. Work done in collaboration with @Paul Riechers, @Lucas Teixeira, @Alexander Gietelink Oldenziel, and Sarah Marzen. Paul was a MATS scholar during some portion of this work. Thanks to Paul, Lucas, Alexander, and @Guillaume Corlouer for suggestions on this writeup.Introduction. What computational structure are we building into LLMs when we train them on

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