PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

5:37

“Safety First: safety before full alignment. The...

LessWrong (30+ Karma) ·

2024/01/03

It could be the case that these two goals are separable and independent: “AI safety”: avoiding existential risk, s-risk, actively negative outcomes“AI getting-everything-we-want” (CEV)This is what Davidad calls this the Deontic Sufficiency Hypothesis. If the hypothesis is true, it should be possible to de-pessimize and mitigate the urgent risk from AI without necessarily ensuring that AI creates actively positive outcomes. Because, for safety, it is only necessary to ensure that actively harmful

en-gb

3:22

[Linkpost] “Practically A Book Review: Appendix to...

LessWrong (30+ Karma) ·

2024/01/03

This is a linkpost for https://thingofthings.substack.com/p/practically-a-book-review-appendixI haven't followed the controversy long enough to be able to tell how correct Ozy is, but what I like about this post is that I find it better structured than some posts, and with better focus on strategically relevant information.For instance, in response to Nonlinear's claim that they weren't isolating Alice and Chloe, Ozy wrote:Kat believes in the importance of digital nomads remaining socially connected

en-gb

31:51

“Copyright Confrontation #1” by Zvi

LessWrong (30+ Karma) ·

2024/01/03

Lawsuits and legal issues over copyright continued to get a lot of attention this week, so I’m gathering those topics into their own post. The ‘virtual #0’ post is the relevant section from last week's roundup. Four Core Claims Who will win the case? Which of New York Times's complaints will be convincing? Different people have different theories of the case. Part of that is that there are four distinct allegations NYT is throwing at the wall. Arvind Narayanan: A thread on some

en-gb

3:20

“Trading off Lives” by jefftk

LessWrong (30+ Karma) ·

2024/01/03

Let's say someone proposes that to reduce deaths from overly chaotic airplane evacuations we ban passenger distractions during the most dangerous parts: takeoff and landing. How could we decide whether a ban like this would be worth it? The argument for the ban is that the safe window for evacuating a plane can be very narrow, and evacuation could potentially go better if everyone were alert. For example, in the 2005 AF358 disaster the plane was completely on fire within ~3min of

en-gb

22:52

“Gentleness and the artificial Other” by Joe Carlsmith

LessWrong (30+ Karma) ·

2024/01/02

(Cross-posted from my website. Audio version here, or search "Joe Carlsmith Audio" on your podcast app. This is the first essay in a series that I’m calling “Otherness and control in the age of AGI.” See here for more about the series as a whole.) When species meet The most succinct argument for AI risk, in my opinion, is the “second species” argument. Basically, it goes like this. Premise 1: AGIs would be like a second advanced species on earth, more powerful than humans. Conclusion: That's

en-gb

10:04

“Apologizing is a Core Rationalist Skill” by...

LessWrong (30+ Karma) ·

2024/01/02

In certain circumstances, apologizing can also be a countersignalling power-move, i.e. “I am so high status that I can grovel a bit without anybody mistaking me for a general groveller”. But that's not really the type of move this post is focused on.There's this narrative about a tradeoff between: The virtue ofSaying Oops, early and often, correcting course rather than continuing to pour oneself into a losing bet, vsThe loss of social status one suffers by admitting defeat, rather than spinning

en-gb

13:57

“OpenAI’s Preparedness Framework: Praise &...

LessWrong (30+ Karma) ·

2024/01/02

In this post, I summarize some of my thoughts on OpenAI's recent preparedness framework. The post focuses on my opinions/analysis of the framework, and it doesn't have much summary (for readers unfamiliar with the framework, I recommend Zvi's post). As a high-level point, I believe voluntary commitments from individual labs will be insufficient, and I'm most excited about policies that governments could apply to all AGI corporations. Nonetheless, I think efforts from individual labs can be useful,

en-gb

81:51

“Dating Roundup #2: If At First You Don’t Succeed” by...

LessWrong (30+ Karma) ·

2024/01/02

Developments around relationships and dating have a relatively small speed premium, also there are once again enough of them for a full post. The first speculated on why you’re still single. We failed to settle the issue. A lot of you are indeed still single. So the debate continues. You’re Single Because You’re Not Even Trying What does it mean to not even be trying? It does not only mean the things Alexander pointed us to last time, like 62% of singles being on zero dating apps,

en-gb

8:01

“AI Is Not Software” by Davidmanheim

LessWrong (30+ Karma) ·

2024/01/02

Epistemic Status: This idea is, I think, widely understood in technical circles. I'm trying to convey it more clearly to a general audience.What we call AI in 2024 is not software. It's kind of natural to put it in the same category as other things that run on a computer, but thinking about LLMs, or image generation, or deepfakes as software is misleading, and confuses most of the ethical, political, and technological discussions. This seems not to be obvious to many users, but as AI gets more

en-gb

17:53

[Linkpost] “Steering Llama-2 with contrastive...

LessWrong (30+ Karma) ·

2024/01/02

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a linkpost for https://arxiv.org/abs/2312.06681The effects of subtracting or adding a "sycophancy vector" to one bias term.TL;DR: By just adding e.g. a "sycophancy vector" to one bias term, we outperform supervised finetuning and few-shot prompting at steering completions to be more or less sycophantic. Furthermore, these techniques are complementary: we show evidence that we can get all three benefits at

en-gb

10:32

“Boston Solstice 2023 Retrospective” by jefftk

LessWrong (30+ Karma) ·

2024/01/02

Saturday evening we held another year's secular solstice celebration ( 2022, 2020, 2019, 2018), and I was again in my music director-ish role. Skyler was the main organizer this time around, with lots of support from Taymon. Scheduling was a bit tricky, as it always is. The weekends closest to astronomical solstice are usually taken by the Bay Area and NYC, and enough people (especially organizers)would like to attend those that it's better if we don't conflict, and then there's

en-gb

6:30

“Stop talking about p(doom)” by Isaac King

LessWrong (30+ Karma) ·

2024/01/01

Epistemic status: Complete speculation, somewhat informed by copious arguing about the subject on Twitter.As AI risk has moved into the mainstream over the past few years, I've come to believe that "p(doom)" is an actively harmful term for X-risk discourse, and people trying to mitigate X-risk should stop using it entirely. AmbiguityThe first problem is that it's unclear what is actually being discussed. "p(doom)" can refer to many different things: p(AI kills us within 5-10 years)p(AI kills us

en-gb

6:26

“2023 in AI predictions” by jessicata

LessWrong (30+ Karma) ·

2024/01/01

Lots of people have made AI predictions in 2023. Here I compile a subset. I have a habit of setting an email reminder for the date of the prediction, when I see AI predictions, so that when they come false I can point this out. I have compiled the email reminders from 2023 in chronological format (predictions with an early to late target date). I'm planning to make these posts yearly, checking in on predictions whose date has expired. Feel free to add more references to predictions made in 2023 to

en-gb

19:33

“Bayesian updating in real life is mostly about...

LessWrong (30+ Karma) ·

2024/01/01

My sense is that an increasingly common viewpoint around here is that the last ~20 years of AI development and AI x-risk discourse are well-described by the following narrative:Eliezer Yudkowsky (and various others who were at least initially heavily influenced by his ideas) developed detailed models of key issues likely to be inherent in the process of developing smarter-than-human AI.These models were somewhere between "maybe plausible" and "quite compelling" at the time that they were put forth,

en-gb

28:30

“A case for AI alignment being difficult” by jessicata

LessWrong (30+ Karma) ·

2023/12/31

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is an attempt to distill a model of AGI alignment that I have gained primarily from thinkers such as Eliezer Yudkowsky (and to a lesser extent Paul Christiano), but explained in my own terms rather than attempting to hew close to these thinkers. I think I would be pretty good at passing an ideological Turing test for Eliezer Yudowsky on AGI alignment difficulty (but not AGI timelines), though what I'm doing in

en-gb

13:40

“AI Alignment Metastrategy” by Vanessa Kosoy

LessWrong (30+ Karma) ·

2023/12/31

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.I call "alignment strategy" the high-level approach to solving the technical problem[1]. For example, value learning is one strategy, while delegating alignment research to AI is another. I call "alignment metastrategy" the high-level approach to converging on solving the technical problem in a manner which is timely and effective. (Examples will follow.)In a previous article, I summarized my criticism of prosaic

en-gb

19:32

“Planning to build a cryptographic box with perfect...

LessWrong (30+ Karma) ·

2023/12/31

Summary. Since September 2023, I started learning a lot of math and programming skills in order to develop the safest cryptographic box in the world (and yes, I am aiming high). In these four months, I learned important things you may want to know: Fully Homomorphic Encryption (FHE) schemes with perfect secrecy do exist.These FHE schemes do not need any computational assumption.These FHE schemes are tractable (in the worst case, encrypting a program before running it makes it three times slower).We

en-gb

4:50

“Taking responsibility and partial derivatives” by Ruby

LessWrong (30+ Karma) ·

2023/12/31

A common pattern for myself over the years is to get into some kind of interpersonal conflict, feel mildly to extremely indignant about how the other person is at fault, then later either through confrontation or reflection, realize that I actually held substantial responsibility. I then feel very guilty.I noticed this pattern some years ago such I did become skeptical of my indignation even when I couldn't yet see where I was responsible. Yet this led me to a feeling of frustration. How is it that

en-gb

7:31

“The proper response to mistakes that have harmed...

LessWrong (30+ Karma) ·

2023/12/31

I have a tendency to feel very guilty when I have harmed others, especially when the harm was quite large. And I do think I've been legitimately quite hurtful and harmful to a number of people over the course of my life.Some of my guilt has persisted for years after recognizing the mistake[1]. I think I prefer this to not feeling remorseful at all, but I do also wonder if I'm responding optimally. I suspect that a form of social anxiety might nudge into excessive feelings of guilt. Guilt done

en-gb

6:46

[Linkpost] “shoes with springs” by bhauth

LessWrong (30+ Karma) ·

2023/12/30

This is a linkpost for https://www.bhauth.com/blog/industrial%20design/spring%20shoes.htmlThere's something intuitively intriguing about the concept of shoes with spring elements, something that made many kids excited about getting "moon shoes", but they found the actual item rather disappointing. Using springs somehow with legged movement also makes some logical sense: walking and running involve cyclic energy changes, and the Achilles tendon stores some elastic energy. Is that perspective missing

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