PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

5:11

“FarmKind’s Illusory Offer” by jefftk

LessWrong (30+ Karma) ·

2024/08/09

While the effective altruism movement has changed a lot over time, oneof the parts that makes me most disappointed is the steady creep of donation matching. It's not that donation matching is objectively very important, but the early EA movement's principled rejection of a very effective fundraising strategy made it clear that we were committed to helping people understand the real impact of their donations. Over time, as people have specialized into different areas of EA, with

en-gb

3:25

“Outrage Bonding” by Jonathan Moregård

LessWrong (30+ Karma) ·

2024/08/09

This is a link post.I stopped following the news back when Trump (first?)[1] got elected. The amount of attention put on a foreign[2] election was staggering, with normal media saccades replaced by Monk-level single-mindedness. Trump was the permanent spotlight for months.The media's fixation on Trump had interesting downstream effects. My peer groups — normally a dynamic bunch — turned into a bunch of snide gossipmongers. Every day was Trump-day, with shared outrage being the primary source of

en-gb

2:17

“Parasites (not a metaphor)” by lukehmiles

LessWrong (30+ Karma) ·

2024/08/09

A few of my new-parent friends started having terrible gut problems and figured they have colon cancer. Their doctors agreed it's the first thing to check. But the colonoscopies were negative for colon cancer. The tissue was inflamed though. One doctor called this "pre-cancer" (??)Hmm what could be causing inflammation in the colon, but wouldn't show up on camera after you fasted and had medically-induced diarrhea for 24 hours? The babies were born over a year before symptoms appeared, so it can't

en-gb

4:07

“GPT-4o System Card” by Zach Stein-Perlman

LessWrong (30+ Karma) ·

2024/08/09

This is a link post.At last. Highlights: some details on Preparedness Framework evals + evals by METR and Apollo. Preparedness framework evaluationsYou should follow the link and read this section.Brief comments: Cyber: the setup sounds good (but maybe substantially more powerful scaffolding/prompting is possible). Separately, I wish OpenAI shared the tasks (or a small random sample of them) or at least said more about where they came from. (Recall that DeepMind shared CTF tasks.)Bio uplift: GPT-4o

en-gb

12:06

“Some Unorthodox Ways To Achieve High GDP Growth” by...

LessWrong (30+ Karma) ·

2024/08/08

GDP growth, as traditionally calculated, is a weird metric. People interpret it as measuring “economic growth”, but… well, think about electronics. Electronics which would have cost millions of dollars (or more) in 1984 are now commonplace, everyone carries them around in their pockets. So if we calculate GDP growth based on 1984 prices, then GDP has grown multiple orders of magnitude since then, everyone now owns things which would make 1984's wealthiest people jealous, and practically all of that

en-gb

22:43

“You can remove GPT2’s LayerNorm by fine-tuning for...

LessWrong (30+ Karma) ·

2024/08/08

This work was produced at Apollo Research, based on initial research done at MATS.LayerNorm is annoying for mechanstic interpretability research (“[...] reason #78 for why interpretability researchers hate LayerNorm” – Anthropic, 2023).Here's a Hugging Face link to a GPT2-small model without any LayerNorm.The final model is only slightly worse than a GPT2 with LayerNorm[1]:DatasetOriginal GPT2Fine-tuned GPT2 with LayerNormFine-tuned GPT without LayerNormOpenWebText(ce_loss)3.0952.9893.014

en-gb

3:41

“Leaving MIRI, Seeking Funding” by abramdemski

LessWrong (30+ Karma) ·

2024/08/08

This is slightly old news at this point, but: as part of MIRI's recent strategy pivot, they've eliminated the Agent Foundations research team. I've been out of a job for a little over a month now. Much of my research time in the first half of the year was eaten up by engaging with the decision process that resulted in this, and later, applying to grants and looking for jobs.I haven't secured funding yet, but for my own sanity & happiness, I am (mostly) taking a break from worrying about that,

en-gb

89:17

“AI #76: Six Shorts Stories About OpenAI” by Zvi

LessWrong (30+ Karma) ·

2024/08/08

If you’re looking forward to next week’s AI #77, I am going on a two-part trip this week. First I’ll be going to Steamboat in Colorado to give a talk, then I’ll be swinging by Washington, DC on Wednesday, although outside of that morning my time there will be limited. My goal is still to get #77 released before Shabbat dinner, we’ll see if that works. Some topics may of course get pushed a bit. It’s crazy how many of this week’s developments are from OpenAI. You’ve got their voice mode alpha, JSON

en-gb

19:50

“[LDSL#0] Some epistemological conundrums” by tailcalled

LessWrong (30+ Karma) ·

2024/08/08

When you deal with statistical science, causal inference, measurement, philosophy, rationalism, discourse, and similar, there's some different questions that pop up, and I think I’ve discovered that there's a shared answer behind a lot of the questions that I have been thinking about. In this post, I will briefly present the questions, and then in a followup post I will try to give my answer for them. Why are people so insistent about outliers?A common statistical method is to assume an outcome is

en-gb

16:16

“It’s time for a self-reproducing machine” by Carl...

LessWrong (30+ Karma) ·

2024/08/08

I've wanted to build a self-reproducing machine since I was 17. It's forty-five years later, and it has finally become feasible. (I've done a few other things along the way.) I'm going to describe one such device, and speculate as to its larger implications. It's a pretty detailed design, which I had to come up with to convince myself that it is feasible. No doubt there are better designs than this. The AutofacHere's a top-level description of the device I'm thinking of. It's called an Autofac,

en-gb

38:24

“WTH is Cerebrolysin, actually?” by gsfitzgerald,...

LessWrong (30+ Karma) ·

2024/08/07

[This article was originally published on Dan Elton's blog, More is Different.]Cerebrolysin is an unregulated medical product made from enzymatically digested pig brain tissue. Hundreds of scientific papers claim that it boosts BDNF, stimulates neurogenesis, and can help treat numerous neural diseases. It is widely used by doctors around the world, especially in Russia and China.A recent video of Bryan Johnson injecting Cerebrolysin has over a million views on X and 570,000 views on YouTube. The

en-gb

61:21

“Startup Roundup #2” by Zvi

LessWrong (30+ Karma) ·

2024/08/06

Previously: Startup Roundup #1.This is my periodic grab bag coverage of various issues surrounding startups, especially but not exclusively tech-and-VC style startups, that apply over the longer term. I always want to emphasize up front that startups are good and you should do one. Equity and skin in the game are where it is at. Building something people want is where it is at. This is true both for a startup that raises venture capital, and also creating an ordinary business. The expected

en-gb

1:40

“John Schulman leaves OpenAI for Anthropic” by Sodium

LessWrong (30+ Karma) ·

2024/08/06

I shared the following note with my OpenAI colleagues today: I've made the difficult decision to leave OpenAI. This choice stems from my desire to deepen my focus on AI alignment, and to start a new chapter of my career where I can return to hands-on technical work. I've decided to pursue this goal at Anthropic, where I believe I can gain new perspectives and do research alongside people deeply engaged with the topics I'm most interested in. To be clear, I'm not leaving due to lack of support for

en-gb

11:03

“We’re not as 3-Dimensional as We Think” by silentbob

LessWrong (30+ Karma) ·

2024/08/06

While thinking about high-dimensional spaces and their less intuitive properties, I came to the realization that even three spatial dimensions possess the potential to overwhelm our basic human intuitions. This post is an exploration of the gap between actual 3D space, and our human capabilities to fathom it. I come to the conclusion that this gap is actually quite large, and we, or at least most of us, are not well equipped to perceive or even imagine “true 3D”.What do I mean by “true 3D”? The most

en-gb

4:01

“How I Learned To Stop Trusting Prediction Markets...

LessWrong (30+ Karma) ·

2024/08/06

This is a story about a flawed Manifold market, about how easy it is to buy significant objective-sounding publicity for your preferred politics, and about why I've downgraded my respect for all but the largest prediction markets.I've had a Manifold account for a while, but I didn't use it much until I saw and became irked by this market on the conditional probabilities of a Harris victory, split by VP pick.Jeb Bush? Really? That's not even a fun kind of wishful thinking for anyone. Please clap.The

en-gb

28:53

“Self-explaining SAE features” by Dmitrii...

LessWrong (30+ Karma) ·

2024/08/06

TL;DR We apply the method of SelfIE/Patchscopes to explain SAE features – we give the model a prompt like “What does X mean?”, replace the residual stream on X with the decoder direction times some scale, and have it generate an explanation. We call thisself-explanation.The natural alternative is auto-interp, using a larger LLM to spot patterns in max activating examples. We show that our method is effective, and comparable with Neuronpedia's auto-interp labels (with the caveat that Neuronpedia's

en-gb

57:37

“Value fragility and AI takeover” by Joe Carlsmith

LessWrong (30+ Karma) ·

2024/08/05

1. Introduction“Value fragility,” as I’ll construe it, is the claim that slightly-different value systems tend to lead in importantly-different directions when subject to extreme optimization. I think the idea of value fragility haunts the AI risk discourse in various ways – and in particular, that it informs a backdrop prior that adequately aligning a superintelligence requires an extremely precise and sophisticated kind of technical and ethical achievement. That is, the thought goes: if you get a

en-gb

16:24

“Circular Reasoning” by abramdemski

LessWrong (30+ Karma) ·

2024/08/05

The idea that circular reasoning is bad is widespread. However, this reputation is undeserved. While circular reasoning should not be convincing (at least not usually), it should also not be considered invalid. Circular Reasoning is ValidThe first important thing to note is that circular reasoning is logically valid. A implies A. If circular arguments are to be critiqued, it must be by some other standard than logical validity.I think it's fair to say that the most relevant objection to circular

en-gb

10:16

“Fear of centralized power vs. fear of misaligned...

LessWrong (30+ Karma) ·

2024/08/05

Vitalik Buterin wrote an impactful blog post, My techno-optimism. I found this discussion of one aspect on 80,00 hours much more interesting. The remainder of that that interview is nicely covered in the host's EA Forum post.My techno optimism apparently appealed to both sides, e/acc and doomers. I'd like to understand how to bridge that polarization better. Buterin's explanation was interesting. I hadn't understood before the extent to which anti-AI regulation sentiment is driven by fear of

en-gb

13:30

“Case Study: Interpreting, Manipulating, and...

LessWrong (30+ Karma) ·

2024/08/05

Click here to open a live research preview where you can try interventions using this SAE. This is a follow-up to a previous post on finding interpretable and steerable features in CLIP. IntroductionCLIP is a neural network commonly used to guide image diffusion. A Sparse Autoencoder was trained on the dense image embeddings CLIP produces to transform it into a sparse representation of active features. These features seem to represent individual units of meaning. They can also be manipulated in

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