PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

5:11

“Learning Math in Time for Alignment” by NicholasKross

LessWrong (30+ Karma) ·

2024/01/09

If you want to do technical AI alignment research, you'll need some amount of non-trivial math knowledge. It may be more theoretical, or with more ML/biology grounding, but it'll definitely be math.How do you learn all this math?"Self-teaching" is almost a misnomer, compared to just "learning". I don't need to distill something for others, I only need myself to grok it. I may use distillation or adjacent techniques to help myself grok it, but like any N=1 self-experiment, it only needs to work for

en-gb

23:36

“A starter guide for evals” by Marius Hobbhahn,...

LessWrong (30+ Karma) ·

2024/01/08

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a linkpost for https://www.apolloresearch.ai/blog/a-starter-guide-for-evalsThis is a starter guide for model evaluations (evals). Our goal is to provide a general overview of what evals are, what skills are helpful for evaluators, potential career trajectories, and possible ways to start in the field of evals. Evals is a nascent field, so many of the following recommendations might change quickly and

en-gb

25:13

“When ‘yang’ goes wrong” by Joe Carlsmith

LessWrong (30+ Karma) ·

2024/01/08

(Cross-posted from my website. Podcast version here, or search "Joe Carlsmith Audio" on your podcast app. This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that the individual essays can be read fairly well on their own, but see here for a brief summary of the essays that have been released thus far.) Becoming God In my last essay, I wrote about "deep atheism" – a fundamental mistrust towards Nature, and towards bare intelligence. I took Eliezer

en-gb

52:52

“2023 Prediction Evaluations” by Zvi

LessWrong (30+ Karma) ·

2024/01/08

It is that time of the year. One must ask not only whether predictions were right or wrong, whether one won or lost, but what one was and should have been thinking, whether or not good decisions were made, whether the market made sense. The main subject will be the 2023 ACX Predictions, where I performed buy/sell/hold along with sharing my logic. The numbers quoted are from mid-February 2023, first Manifold, then Metaculus. Section 1: World Politics Will Vladimir Putin be President

en-gb

18:56

“Reflections on my first year of AI safety research”...

LessWrong (30+ Karma) ·

2024/01/08

Last year, I wrote a post about my upskilling in AI alignment. To this day, I still get people occasionally reaching out to me because of this article, to ask questions about getting into the field themselves. I’ve also had several occasions to link people to the article who asked me about getting into the field from other means, like my local AI Safety group. Essentially, what this means is that people clearly found this useful (credit to the EA Forum for managing to let the article be findable

en-gb

21:46

[Linkpost] “A model of research skill” by L Rudolf L

LessWrong (30+ Karma) ·

2024/01/08

This is a linkpost for https://www.strataoftheworld.com/2024/01/a-model-of-research-skill.htmlDoing research means answering questions no one yet knows the answer to. Lots of impactful projects are downstream of being good at this. A good first step is to have a model for what the hard parts of research skill are. Two failure modesThere are two opposing failure modes you can fall into when thinking about research skill.The first is the deferential one. Research skill is this amorphous complicated

en-gb

10:41

“Deceptive AI ≠ Deceptively-aligned AI” by Steven Byrnes

LessWrong (30+ Karma) ·

2024/01/07

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.Tl;dr: A “deceptively-aligned AI” is different from (and much more specific than) a “deceptive AI”. I think this is well-known and uncontroversial among AI Alignment experts, but I see people getting confused about it sometimes, so this post is a brief explanation of how they differ. You can just look at the diagram below for the upshot.Some motivating context: There have been a number of recent arguments that

en-gb

16:57

[Linkpost] “Bayesians Commit the Gambler’s Fallacy”...

LessWrong (30+ Karma) ·

2024/01/07

This is a linkpost for https://kevindorst.substack.com/p/bayesians-commit-the-gamblers-fallacyTLDR: Rational people who start out uncertain about an (in fact independent) causal process and then learn from unbiased data will rule out “streaky” hypotheses more quickly than “switchy” hypotheses. As a result, they’ll commit the gambler's fallacy: expecting the process to switch more than it will. In fact, they’ll do so in ways that match a variety of empirical findings about how real people commit the

en-gb

64:07

[Linkpost] “Defending against hypothetical moon life...

LessWrong (30+ Karma) ·

2024/01/07

This is a linkpost for https://eukaryotewritesblog.com/2024/01/06/defending-against-hypothetical-moon-life-during-apollo-11/[Header image: Photo of the lunar lander taken during Apollo 11.]In 1969, after successfully bringing men back from landing on the moon, the astronauts, spacecraft, and all the samples from the moon surface were quarantined for 21 days. This was to account for the possibility that they were carrying hostile moon germs. Once the quarantine was up and the astronauts were not

en-gb

10:23

“AI Risk and the US Presidential Candidates” by Zane

LessWrong (30+ Karma) ·

2024/01/06

It's the new year, and the 2024 primaries are approaching, starting with New Hampshire on January 23rd. For a lot of people here on LessWrong, the issue of AI risk will likely be an important factor in making a decision. AI hasn't been mentioned much during any of the candidates' campaigns, but I'm attempting to analyze the information that there is, and determine which candidate is most likely to bring about a good outcome.A few background facts about my own position - such that if these statements

en-gb

4:24

“Survey of 2,778 AI authors: six parts in pictures”...

LessWrong (30+ Karma) ·

2024/01/06

Crossposted from AI Impacts blogThe 2023 Expert Survey on Progress in AI is out, this time with 2778 participants from six top AI venues (up from about 700 and two in the 2022 ESPAI), making it probably the biggest ever survey of AI researchers.People answered in October, an eventful fourteen months after the 2022 survey, which had mostly identical questions for comparison.Here is the preprint. And here are six interesting bits in pictures (with figure numbers matching paper, for ease of learning

en-gb

33:40

[Linkpost] “Project ideas: Epistemics” by Lukas...

LessWrong (30+ Karma) ·

2024/01/05

This is a linkpost for https://lukasfinnveden.substack.com/p/project-ideas-epistemics This is part of a series of lists of projects. The unifying theme is that the projects are not targeted at solving alignment or engineered pandemics but still targeted at worlds where transformative AI is coming in the next 10 years or so. See here for the introductory post. If AI capabilities keep improving, AI could soon play a huge role in our epistemic landscape. I think we have an opportunity to affect how

en-gb

18:37

[Linkpost] “Almost everyone I’ve met would be...

LessWrong (30+ Karma) ·

2024/01/05

This is a linkpost for https://www.henrikkarlsson.xyz/p/multi-armed-banditAlmost everyone I’ve ever met would be well-served by spending more time thinking about what to focus on. —Sam AltmanIn May 2020, we parked two moving trucks in the harbor and carried everything we owned from one to the other. Johanna, Maud, and I were leaving Sweden, and Covid restrictions meant we were forbidden from returning once we boarded the ferry. Hence the second truck, which we had gotten a stranger to ferry from the

en-gb

3:09

“The Next ChatGPT Moment: AI Avatars” by kolmplex,...

LessWrong (30+ Karma) ·

2024/01/05

Epistemic Status: Speculative. Dependent on intuitions about near-term AI tech and human psychology.Claim: Within the next 1-3 years, many people will have an interaction with an AI avatar that feels authentically human. This will significantly amplify the public perception of current AI capabilities and risks.An AI avatar is a realistic AI-generated render of a human (speech and video) that can have a real-time conversation with a human, for example over a video call.The individual components

en-gb

41:34

“Catching AIs red-handed” by ryan_greenblatt, Buck

LessWrong (30+ Karma) ·

2024/01/05

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.We’ve been spending a lot of time recently thinking about how to mitigate risks posed by scheming (a.k.a. deceptively aligned) models intentionally subverting your safety techniques in order to cause an unacceptable outcome. We empirically investigated techniques that are robust to intentional subversion in our recent paper.In this post, we’ll discuss a crucial dynamic related to risk from scheming models. Suppose

en-gb

14:07

“MIRI 2024 Mission and Strategy Update” by Malo

LessWrong (30+ Karma) ·

2024/01/05

As we announced back in October, I have taken on the senior leadership role at MIRI as its CEO. It's a big pair of shoes to fill, and an awesome responsibility that I’m honored to take on.There have been several changes at MIRI since our 2020 strategic update, so let's get into it.[1]The short version:We think it's very unlikely that the AI alignment field will be able to make progress quickly enough to prevent human extinction and the loss of the future's potential value, that we expect will result

en-gb

52:36

“Deep atheism and AI risk” by Joe Carlsmith

LessWrong (30+ Karma) ·

2024/01/04

(Cross-posted from my website. Audio version here, or search "Joe Carlsmith Audio" on your podcast app. This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that the individual essays can be read fairly well on their own, but see here for a summary of the essays that have been released thus far, and for a bit more about the series as a whole.) In my last essay, I talked about the possibility of "gentleness" towards various non-human Others – for example,

en-gb

1:20

“Some Vacation Photos” by johnswentworth

LessWrong (30+ Karma) ·

2024/01/04

In the past three months, I've flown overnight from San Francisco to the UK/Europe three times.Three times, I got a window seat on the left side of the plane.And three times... well, see for yourself.First tripSecond tripThird tripKey thing to know: these aurora did not look like this to the naked eye. They were usually too faint to see the color at all; they looked like faint moonlight shining around the edges of a dark cloud. Except the "cloud" was higher up than an airplane flying at 10+ km.It

en-gb

55:19

“AI #45: To Be Determined” by Zvi

LessWrong (30+ Karma) ·

2024/01/04

The first half of the week was filled with continued talk about the New York Times lawsuit against OpenAI, which I covered in its own post. Then that talk seemed to mostly die down,, and things were relatively quiet. We got a bunch of predictions for 2024, and I experimented with prediction markets for many of them. Note that if you want to help contribute in a fun, free and low-key, participating in my prediction markets on Manifold is a way to do that. Each new participant in each market, even

en-gb

28:55

“What’s up with LLMs representing XORs of arbitrary...

LessWrong (30+ Karma) ·

2024/01/03

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.Thanks to Clément Dumas, Nikola Jurković, Nora Belrose, Arthur Conmy, and Oam Patel for feedback.In the comments of the post on Google Deepmind's CCS challenges paper, I expressed skepticism that some of the experimental results seemed possible. When addressing my concerns, Rohin Shah made some claims along the lines of “If an LLM linearly represents features a and b, then it will also linearly represent their XOR,

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