Audio narrations of LessWrong posts.
When I was growing up most families in our neighborhood had the daily paper on their lawn. As gett
IntroAnthropic recently released an exciting mini-paper on crosscoders (Lindsey et al.). In this po
This is a link post.A small number of terms are elevated from the pages of literature, up to the Mou
Epistemic status: model-building based on observation, with a few successful unusual predictions. An
This is a link post.This is a YouTube playlist of recorded lectures on the learning-theoretic AI ali
Airships are pretty dang cool. Airplanes need a continuous expenditure of energy to stay in the air,
We are pleased to announce that the 10th version of the AI Safety Camp is now entering the team memb
[Linkpost. This presents a way to talk to people about AI that hold overly-romanticized views built
This is a link post. Memorandum on Advancing the United States’ Leadership in Artificial Intelligenc
This is a link post. As artificial intelligence (AI) systems become more advanced, concerns about la
The first practical steam engine was built by Thomas Newcomen in 1712. It was used to pump water out
I'm a research lead at Timaeus and attended a workshop that @Raemon ran from Oct 4-6 (it was shorten
Anthropic has released an upgraded Claude Sonnet 3.5, and the new Claude Haiku 3.5. They claim ac
Summary In this post, we explore different ways of understanding and measuring malevolence and expl
Audio note: this article contains 241 uses of latex notation, so the narration may be difficult to
"Garbage in, garbage out" — Someone in Machine Learning TL;DR: This post is a two-page introduction
This is the full text of a post from "The Obsolete Newsletter," a Substack that I write about the in
TL;DR:In our recent work with Professor Michael Graziano (arXiv, thread), we show that adding an au
We are launching an independent research lab that builds open, scalable technology for understanding
This post includes a "flattened version" of an interactive diagram that cannot be displayed on this
