Technology

LessWrong (30+ Karma)

by LessWrong

TechnologySociety & CulturePhilosophy

Is this your show? Claim it

Listen on Apple Podcasts RSS feed

Recently ranked · United States

Last recorded placements from this show’s chart history. These are not current rankings.

Not on the United States charts we track today.

If you like LessWrong (30+ Karma), try…

LessWrong (Curated & Popular)

From LessWrong

LessWrong posts by zvi

Latest episodes

“Measuring agent capabilities on open-ended AI R&D tasks” by Alex Jackson, Titus Buckworth, Jason R Brown, Francis Rhys Ward

October 27, 2026 · 36 min

TL;DR. We measure agent capabilities on four long and open-ended research tasks. Frontier models have been improving with an overall doubling time of around one year since 2024 (based on an exponential fit). Agents perform better at…
“The AI buildout is the largest bet in the history of capitalism. Key decision makers believe very powerful AI will be achieved soon.” by Hayekstan

October 27, 2026 · 7 min

This is part linkpost, and an expansion on a previous shortform posted on LW. I believe a massively undermade point in favour of the belief that AI will be a very big deal is that the AI buildout over the past four years is the largest…
“Hair Thickness of My Friends” by XelaP

October 26, 2026 · 7 min

Intro I have a microscope. It can see hair. Humans have hair. Some of my friends are humans. How thick is my friends' hair? Apparently, if I go around asking my friends for a strand of their hair, about half will just give one to me…
“A basic case for differentially accelerating conceptual reasoning capabilities” by Emery Cooper, Caspar Oesterheld, Chi Nguyen

October 26, 2026 · 50 min

Introduction In this post, we make the case that alignment and other important work require especially strong conceptual reasoning capabilities. By this, we roughly mean tasks that are similar to philosophy in that they aren't…
“A cat-belling problem for FDT” by jessicata

October 26, 2026 · 20 min

Audio note: this post contains a lot of mathematical notation. We narrate the simpler formulas and flag the complex ones, so you may want the original text to hand. [AI disclosure: I used Opus 5.5 for light edits after my first draft]…

Show 7 more episodesShow fewer episodes

“Anthropic are the Good Guys” by Ivan Vendrov

October 26, 2026 · 21 min

I’m writing these lines in Alamogordo, New Mexico. I’m about as close as a civilian can get to the site of the Trinity test, the first nuclear bomb detonation in history. I fled here from the San Francisco Bay Area; after two weeks of…
“Some Memories of Early Anthropic” by Ivan Vendrov

October 26, 2026 · 17 min

The following events took place between October 2022 and May 2023. I wrote very little of this down at the time so am recalling from memory, and am rendering the gist of the dialogue rather than the exact words used. I’ve also swapped some…
“Is GPT 2XL already clean?” by Jasper Blank

October 26, 2026 · 12 min

In which I investigate if Opus is able to interpret neurons better than GPT 4. TLDR: Opus 5.5 is able to identify 3-19% of the neurons of GPT 2-XL based on activations. This is a big improvement over the 0.3% that GPT-4 was able to…
“LoReFT GRAFT Better at Preventing RL Grift” by Samuel Knoche

October 25, 2026 · 8 min

tl;dr. I show that the recently introduced GRAFT method can be improved upon by using a single layer rank 1 Low-rank Linear Subspace Representation Fine Tuning (LoReFT) adapter as the FORGET adapter, using only 0.029% of the parameters of…
“A Study of China Does Not Personal Experience Make” by celesteli

October 25, 2026 · 9 min

I am often skeptical of arguments about China that rely heavily on personal experience. The author may explicitly acknowledge that their experience is limited without appropriately treating their arguments with rigor beforehand. This…
“San Francisco State University in Twilight” by Zack_M_Davis

October 25, 2026 · 16 min

You will agree that for a woman who has fought three duels, all of them kills, indulging in such fears is ludicrous. But what's around the corner now is a duel so big that I don't think I have the guts for it; in Faust's words: Verweile…
“From overeliciting to undereliciting LLM propensities in just a few months” by David Africa

October 25, 2026 · 4 min

For a while, we felt we had a pretty good grasp over LLM behaviour because we had to exert significant effort to elicit misaligned behaviour. Then, fairly suddenly, we moved to undereliciting misaligned behaviour. Let us recount: For a…