PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

12:33

“Mistakes people make when thinking about units” by...

LessWrong (30+ Karma) ·

2024/06/25

This is a linkpost for Parker Dimensional Analysis. Probably a little elementary for LessWrong, but I think it may still contain a few novel insights, particularly in the last section about Verison's error.A couple years ago, there was an interesting clip on MSNBC.A few weeks later, Matt Parker came out with a video analyzing why people tend to make mistakes like this. Now I'm normally a huge fan of Matt Parker. But in this case, I think he kinda dropped the ball.He does have a very good insight. He

en-gb

17:08

“Formal verification, heuristic explanations and...

LessWrong (30+ Karma) ·

2024/06/25

ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understanding of what was going on inside a neural network, we would hope to be able to use that understanding to verify that the network was not going to behave dangerously in unforeseen situations. ARC is attempting to perform this kind of verification, but using a mathematical kind of "explanation" instead of one written in natural language.To help elucidate

en-gb

1:01

“I’m a bit skeptical of AlphaFold 3” by Oleg Trott

LessWrong (30+ Karma) ·

2024/06/25

This is a link post.So this happened: DeepMind (with 48 authors, including a new member of the British nobility) decided to compete with me. Or rather, with some of my work from 10+ years ago.Apparently, AlphaFold 3 can now predict how a given drug-like molecule will bind to its target protein. And it does so better than AutoDock Vina (the most cited molecular docking program, which I built at Scripps Research).On top of this, it doesn’t even need a 3D structure of the target. It predicts it too!But

en-gb

63:38

“Book Review: Righteous Victims - A History of the...

LessWrong (30+ Karma) ·

2024/06/25

I originally entered this to the ACX Book Review competition. Since it has not been selected as a finalist I'm now free to post it here. In truth it's a followup to my review of Morris's history of Israel's War of Independence.In the wake of the October 7th attack on Israel and Israel's response, everyone seemed to agree that one side of the conflict was the epitome of evil, the reincarnation of the Nazis, with warfare in their blood and a pure unfiltered hatred of the enemy in their minds. The

en-gb

6:14

“Higher-effort summer solstice: What if we used AI...

LessWrong (30+ Karma) ·

2024/06/25

As the title probably already indicates, this post contains community content rather than rationality content. Alternate, sillier version of this post here. MotivationI've been a co-organizer of the Bay Area Rationalist Summer Solstice for the past few years, and I've been thinking about how to make it a more meaningful and engaging experience, like what we have with Winter Solstice. The last few Summer Solstices, which I'd describe as mostly being big picnics, have been fun, but fairly low-effort,

en-gb

10:34

“The Minority Faction” by Richard_Ngo

LessWrong (30+ Karma) ·

2024/06/25

This is a link post.Hey everyone. Well, possibly everyone. I don’t know yet if I’m going to release this stream, I could get in pretty hot water for it. But you guys know that hasn’t stopped me in the past. The backstory this time is that I’ve managed to sign up for one of the red-teaming programs where they test unreleased LLMs. Not going to say how, so don’t ask. But here's the interesting bit: my sources tell me that the LLMs I’m about to test are the smartest ones they’ve ever trained, and also

en-gb

23:41

“So you want to work on technical AI safety” by gw

LessWrong (30+ Karma) ·

2024/06/24

I’ve been to two EAGx events and one EAG, and the vast majority of my one on ones with junior people end up covering some subset of these questions. I’m happy to have such conversations, but hopefully this is more efficient and wide-reaching (and more than I could fit into a 30 minute conversation).I am specifically aiming to cover advice on getting a job in empirically-leaning technical research (interp, evals, red-teaming, oversight, etc) for new or aspiring researchers without being overly

en-gb

10:10

“Sci-Fi books micro-reviews” by Yair Halberstadt

LessWrong (30+ Karma) ·

2024/06/24

I've recently been reading a lot of science fiction. Most won't be original to fans of the genre, but some people might be looking for suggestions, so in lieu of full blown reviews here's super brief ratings on all of them. I might keep this updated over time, if so new books will go to the top. A deepness in the sky (Verner Vinge)scifiosity: 10/10 readability: 8/10 recommended: 10/10A deepness in the sky excels in its depiction of a spacefaring civilisation using no technologies we know to be

en-gb

13:55

“Compact Proofs of Model Performance via Mechanistic...

LessWrong (30+ Karma) ·

2024/06/24

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.We recently released a paper on using mechanistic interpretability to generate compact formal guarantees on model performance. In this companion blog post to our paper, we'll summarize the paper and flesh out some of the motivation and inspiration behind our work. Paper abstractIn this work, we propose using mechanistic interpretability – techniques for reverse engineering model weights into

en-gb

18:30

“SAE feature geometry is outside the superposition...

LessWrong (30+ Karma) ·

2024/06/24

Summary: Superposition-based interpretations of neural network activation spaces are incomplete. The specific locations of feature vectors contain crucial structural information beyond superposition, as seen in circular arrangements of day-of-the-week features and in the rich structures. We don’t currently have good concepts for talking about this structure in feature geometry, but it is likely very important for model computation. An eventual understanding of feature geometry might look like a

en-gb

26:22

“On Claude 3.5 Sonnet” by Zvi

LessWrong (30+ Karma) ·

2024/06/24

There is a new clear best (non-tiny) LLM.If you want to converse with an LLM, the correct answer is Claude Sonnet 3.5. It is available for free on Claude.ai and the Claude iOS app, or you can subscribe for higher rate limits. The API cost is $3 per million input tokens and $15 per million output tokens. This completes the trifecta. All of OpenAI, Google DeepMind and Anthropic have kept their biggest and more expensive model static for now, and instead focused on making something faster and

en-gb

13:09

“LLM Generality is a Timeline Crux” by eggsyntax

LessWrong (30+ Karma) ·

2024/06/24

Summary Summary . LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible. Longer summaryThere is ML research suggesting that LLMs fail badly on attempts at general reasoning, such as planning problems, scheduling, and attempts to solve novel visual puzzles. This post provides a brief introduction to that research, and asks: Whether this limitation is illusory or actually exists.If it exists, whether it will be solved by scaling or is a problem

en-gb

14:43

“LLM Generality is a Timeline Crux” by eggsyntax

LessWrong (30+ Karma) ·

2024/06/24

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Short SummaryLLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible. Longer summaryThere is ML research suggesting that LLMs fail badly on attempts at general reasoning, such as planning problems, scheduling, and attempts to solve novel visual puzzles. This post provides a brief introduction to that research, and asks: Whether this limitation is illusory or

en-gb

9:04

“Different senses in which two AIs can be ‘the same’”...

LessWrong (30+ Karma) ·

2024/06/24

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.Sometimes people talk about two AIs being “the same” or “different” AIs. We think the intuitive binary of “same vs. different” conflates several concepts which are often better to disambiguate. In this post, we spell out some of these distinctions. We don’t think anything here is particularly novel; we wrote this post because we think it's probably mildly helpful for people to think this through, and because Buck

en-gb

15:32

“Applying Force to the Wrong End of a Causal Chain”...

LessWrong (30+ Karma) ·

2024/06/23

A causal chain. Obviously.There's a very common thing that humans do: a person makes an observation about something they dislike, so they go ahead and make an effort to change that thing. Sometimes it works, and sometimes it doesn’t. If it doesn’t work, there can be a variety of reasons for that – maybe the thing is very difficult to change, maybe the person lacks the specific skills to change the thing, maybe it depends on the behavior of other people and the person is not successful in convincing

en-gb

7:29

“I would have shit in that alley, too” by Declan Molony

LessWrong (30+ Karma) ·

2024/06/23

After living in a suburb for most of my life, when I moved to a major U.S. city the first thing I noticed was the feces. At first I assumed it was dog poop, but my naivety didn’t last long.One day I saw a homeless man waddling towards me at a fast speed while holding his ass cheeks. He turned into an alley and took a shit. As I passed him, there was a moment where our eyes met. He sheepishly averted his gaze.The next day I walked to the same place. There are a number of businesses on both sides of

en-gb

35:26

“Getting 50% (SoTA) on ARC-AGI with GPT-4o” by...

LessWrong (30+ Karma) ·

2024/06/23

ARC-AGI post Getting 50% (SoTA) on ARC-AGI with GPT-4oI recently got to 50%[1] accuracy on the public test set for ARC-AGI by having GPT-4o generate a huge number of Python implementations of the transformation rule (around 8,000 per problem) and then selecting among these implementations based on correctness of the Python programs on the examples (if this is confusing, go here)[2]. I use a variety of additional approaches and tweaks which overall substantially improve the performance of my method

en-gb

5:29

“Enriched tab is now the default LW Frontpage...

LessWrong (30+ Karma) ·

2024/06/23

In the past few months, the LessWrong team has been making use of the latest AI tools (given that they unfortunately exist[1]) for art, music, and deciding what we should all be reading.Our experiments with the latter, i.e. the algorithm that chooses which posts to show on the frontpage, has produced results sufficiently good that at least for now, we're making Enriched the default for logged-in users[2]. If you're logged in and you've never switched tabs before, you'll now be on the Enriched tab

en-gb

2:16

“Bed Time Quests & Dinner Games for 3-5 year olds” by...

LessWrong (30+ Karma) ·

2024/06/23

This is a link post.I like these games because they are playful, engage the child and still achieve the objective of getting the child to bed/eat dinner etc. Requires creativity and some slack. Excerpt from Shohannah's post:Recently I had the bright idea to give up on being a regular parent. Mostly cause regular parenting practices melt my brain. But then I wondered … does it have to be boring?[...]But no. It's all culture and it's all recent culture and you can decide to do Something Else Instead

en-gb

56:04

“On OpenAI’s Model Spec” by Zvi

LessWrong (30+ Karma) ·

2024/06/22

There are multiple excellent reasons to publish a Model Spec like OpenAI's, that specifies how you want your model to respond in various potential situations. It lets us have the debate over how we want the model to act. It gives us a way to specify what changes we might request or require. It lets us identify whether a model response is intended. It lets us know if the company successfully matched its spec. It lets users and prospective users know what to expect. It gives

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