PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

3:35

“Mud and Despair (Part 4 of ‘The Sense Of Physical...

LessWrong (30+ Karma) ·

2024/03/07

This is the fourth post in a sequence that demonstrates a complete naturalist study, specifically a study of query hugging (sort of), as described in The Nuts and Bolts of Naturalism. For context on this sequence, see the intro post. “Mud and Despair” is not officially one of the phases of naturalism. Unofficially, though, it's the phase that often happens somewhere between “Getting Your Eyes On” and “Collection”. When I look back at my notes from this part of my study (roughly mid September), I am

en-gb

45:32

“Social status part 1/2: negotiations over...

LessWrong (30+ Karma) ·

2024/03/07

1.1 Summary & contentsThis is the first of two blog posts where I try to make sense of the whole universe of social-status-related behaviors and phenomena: This post is focused on a special case of two people interacting, where they have different object-level preferences—maybe one wants to order pizza for dinner while the other wants sushi. This gets us into various topics like “leading and following”, averaging different people's utility functions, being more or less “pushy”, “ask culture

en-gb

4:01

“Movie posters” by KatjaGrace

LessWrong (30+ Karma) ·

2024/03/07

Life involves anticipations. Hopes, dreads, lookings forward. Looking forward and hoping seem pretty nice, but people are often wary of them, because hoping and then having your hopes fold can be miserable to the point of offsetting the original hope's sweetness. Even with very minor hopes: he who has harbored an inchoate desire to eat ice cream all day, coming home to find no ice cream in the freezer, may be more miffed than he who never tasted such hopes. And this problem is made worse by that

en-gb

22:04

[Linkpost] “Research Report: Sparse Autoencoders find...

LessWrong (30+ Karma) ·

2024/03/06

This is a linkpost for https://aizi.substack.com/p/research-report-sparse-autoencodersAbstract. A sparse autoencoder is a neural network architecture that has recently gained popularity as a technique to find interpretable features in language models (Cunningham et al, Anthropic's Bricken et al). We train a sparse autoencoder on OthelloGPT, a language model trained on transcripts of the board game Othello, which has been shown to contain a linear representation of the board state, findable by

en-gb

58:23

“On Claude 3.0” by Zvi

LessWrong (30+ Karma) ·

2024/03/06

Claude 3.0 Claude 3.0 is here. It is too early to know for certain how capable it is, but Claude 3.0's largest version is in a similar class to GPT-4 and Gemini Advanced. It could plausibly now be the best model for many practical uses, with praise especially coming in on coding and creative writing. Anthropic has decided to name its three different size models Opus, Sonnet and Haiku, with Opus only available if you pay. Can we just use Large, Medium and Small? Cost varies quite a lot

en-gb

1:07

“Vote on Anthropic Topics to Discuss” by Ben Pace

LessWrong (30+ Karma) ·

2024/03/06

What important questions would you want to see discussed and debated here about Anthropic? Suggest and vote below. How to use the poll Reacts: Click on the agree/disagree reacts to help people see how much disagreement there is on the topic. Karma: Upvote positions that you'd like to read discussion about. New Poll Option: Add new positions for people to take sides on. Please add the agree/disagree reacts to new poll options you make. The goal is to show people where a lot of interest

en-gb

8:46

[Linkpost] “Using axis lines for good or evil” by...

LessWrong (30+ Karma) ·

2024/03/06

This is a linkpost for https://dynomight.net/axes/Say you want to plot some data. You could just plot it by itself:Or you could put lines on the left and bottom:Or you could put lines everywhere:Or you could be weird:Which is right? Many people treat this as an aesthetic choice. But I’d like to suggest an unambiguous rule. PrinciplesFirst, try to accept that all axis lines are optional. I promise that readers will recognize a plot even without lines around it.So consider these plots:Which is better

en-gb

21:55

“We Inspected Every Head In GPT-2 Small using SAEs So...

LessWrong (30+ Karma) ·

2024/03/06

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 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 trainedattention SAEs onevery layer ofGPT-2 Small and we found that a majority of features are interpretable in all layers. We’ve since leveraged

en-gb

13:20

“My Clients, The Liars” by ymeskhout

LessWrong (30+ Karma) ·

2024/03/05

It's not just that my clients lie to me a lot, which will only hurt them — it's that they’re really, really bad at it.My job as a public defender puts me in a weird place. I am my clients’ zealous advocate, but I’m not their marionette. I don’t just roll into court to parrot whatever my clients tell me — I make sure I’m not re-shoveling bullshit. So for my sake and theirs, I do my homework. I corroborate. I investigate.A significant portion of my job ironically mirrors that of a police detective

en-gb

33:18

“Read the Roon” by Zvi

LessWrong (30+ Karma) ·

2024/03/05

Roon, member of OpenAI's technical staff, is one of the few candidates for a Worthy Opponent when discussing questions of AI capabilities development, AI existential risk and what we should do about it. Roon is alive. Roon is thinking. Roon clearly values good things over bad things. Roon is engaging with the actual questions, rather than denying or hiding from them, and unafraid to call all sorts of idiots idiots. As his profile once said, he believes spice must flow, we just do go ahead, and makes

en-gb

20:04

“Many arguments for AI x-risk are wrong” by TurnTrout

LessWrong (30+ Karma) ·

2024/03/05

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.The following is a lightly edited version of a memo I wrote for a retreat. It was inspired by a draft of Counting arguments provide no evidence for AI doom , although the earlier draft contained some additional content. I personally really like the earlier content, and think that my post covers important points not made by the published version of that post. Thankful for the dozens of interesting conversations and

en-gb

2:36

[Linkpost] “Anthropic release Claude 3, claims GPT-4...

LessWrong (30+ Karma) ·

2024/03/04

This is a linkpost for https://www.anthropic.com/news/claude-3-familyToday, we're announcing the Claude 3 model family, which sets new industry benchmarks across a wide range of cognitive tasks. The family includes three state-of-the-art models in ascending order of capability: Claude 3 Haiku, Claude 3 Sonnet, and Claude 3 Opus. Each successive model offers increasingly powerful performance, allowing users to select the optimal balance of intelligence, speed, and cost for their specific

en-gb

87:03

“Housing Roundup #7” by Zvi

LessWrong (30+ Karma) ·

2024/03/04

Legalize housing. It is both a good slogan and also a good idea. The struggle is real, ongoing and ever-present. Do not sleep on it. The Housing Theory of Everything applies broadly, even to the issue of AI. If we built enough housing that life vastly improved and people could envision a positive future, they would be far more inclined to think well about AI. In Brief What will AI do to housing? If we consider what the author here calls a ‘reasonably optimistic’ scenario and what I’d

en-gb

4:15

“Are we so good to simulate?” by KatjaGrace

LessWrong (30+ Karma) ·

2024/03/04

If you believe that,— a) a civilization like ours is likely to survive into technological incredibleness, and b) a technologically incredible civilization is very likely to create ‘ancestor simulations’, —then the Simulation Argument says you should expect that you are currently in such an ancestor simulation, rather than in the genuine historical civilization that later gives rise to an abundance of future people. Not officially included in the argument I think, but commonly believed: both a)

en-gb

4:35

“The Broken Screwdriver and other parables” by bhauth

LessWrong (30+ Karma) ·

2024/03/04

previously: The Parable Of The Fallen Pendulum The Broken Screwdriver Alice: Hey Bob, I need something to put this screw in the wall. Bob: OK, here's a screwdriver. Alice starts trying to hammer a screw in using the butt of the screwdriver. Alice: I think this screwdriver is broken. Bob: You're not using it correctly, you have to fit the other end inside the screw and twist the screw in. Alice tries doing that. Alice: It's still not working. Bob: You're using the hex bit, you need to swap it

en-gb

8:11

“Grief is a fire sale” by Nathan Young

LessWrong (30+ Karma) ·

2024/03/04

For me, grief is often about the future. It isn't about the loss of past times, since those were already gone. It is the loss of hope. It's missing the last train to a friends wedding or never being able to hear another of my grandfathers sarcastic quips.In the moment of grief, it is the feeling of disorientation between a previous expected future and what the future looks like now. I can still feel anticipation for that set of worlds, but it is almost worthless. And it is agony, a phantom limb.One

en-gb

42:12

“AI things that are perhaps as important as...

LessWrong (30+ Karma) ·

2024/03/03

Topic of the post: I list potential things to work on other than keeping AI under human control. Motivation The EA community has long been worried about AI safety. Most of the efforts going into AI safety are focused on making sure humans are able to control AI. Regardless of whether we succeed at this, I think there's a lot of additional value on the line. First of all, if we succeed at keeping AI under human control, there are still a lot of things that can go wrong. My perception is that this

en-gb

6:34

“Some costs of superposition” by Linda Linsefors

LessWrong (30+ Karma) ·

2024/03/03

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.I don't expect this post to contain anything novel. But from talking to others it seems like some of what I have to say in this post is not widely known, so it seemed worth writing. In this post I'm defining superposition as: A representation with more features than neurons, achieved by encoding the features as almost orthogonal vectors in neuron space.One reason to expect superposition in neural nets (NNs), is

en-gb

5:45

[Linkpost] “Self-Resolving Prediction Markets” by...

LessWrong (30+ Karma) ·

2024/03/03

This is a linkpost for https://bayesianinvestor.com/blog/index.php/2024/03/02/self-resolving-prediction-markets/Back in 2008, I criticized the book Predictocracy for proposing prediction markets whose contracts would be resolved without reference to ground truth. Recently, Srinivasan, Karger, and Chen (SKC) published more scholarly paper titled Self-Resolving Prediction Markets for Unverifiable Outcomes. Manipulation In the naive version of self-resolving markets that I think Predictocracy

en-gb

95:08

[Linkpost] “Agreeing With Stalin in Ways That Exhibit...

LessWrong (30+ Karma) ·

2024/03/02

This is a linkpost for http://unremediatedgender.space/2024/Mar/agreeing-with-stalin-in-ways-that-exhibit-generally-rationalist-principles/ It was not the sight of Mitchum that made him sit still in horror. It was the realization that there was no one he could call to expose this thing and stop it—no superior anywhere on the line, from Colorado to Omaha to New York. They were in on it, all of them, they were doing the same, they had given Mitchum the lead and the method. It was Dave Mitchum who now

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