Audio narrations of LessWrong posts.
This post should not be taken as a polished recommendation to AI companies and instead should be tre
This is a link post.Dario corrects misconceptions and endorses export controls.Also:DeepSeek does no
No one is talking about OpenAI's Operator. We’re, shall we say, a bit distracted. It's still a rathe
This is a link post.TL;DR: This paper brings together ~30 mech interp researchers from 18 different
(Audio version here, or search for "Joe Carlsmith Audio" on your podcast app.)“There comes a moment
DeepSeek released v3. Market didn’t react. DeepSeek released r1. Market didn’t react. DeepSeek relea
Cross-posted on the EA Forum here IntroductionSeveral developments over the past few months should c
Summary and Table of ContentsThe goal of this post is to discuss the so-called “sharp left turn”, t
(Many of these ideas developed in conversation with Ryan Greenblatt)In a shortform, I described some
One restatement of "Alignment is very hard" is "Agent X, with IQ 200, expects to achieve zero utilit
Audio note: this article contains 88 uses of latex notation, so the narration may be difficult to
When I started graduate school (for math), I was very interested in big ideas. I had had a couple ex
It started as so many dooms do, with a flash in the night sky over the South China Sea. Testing a ne
In this new paper, I discuss what it would mean for AI systems to be persons — entities with propert
January: In early 2026, Meta launches a fleet of new AI influencers, targeting the massive audience
The Attorney General of Massachusetts recently announced that drivers for ride-sharing companies mus
And then we hit a wall. Nobody expected it. Well... almost nobody. Yann LeCun posted his "I told you
“Anomalous”, “glitch”, or “unspeakable” tokens in an LLM are those that induce bizarre behavior or o
[Epistemic status: slightly ranty. This is a lightly edited slack chat, and so may be lower-quality.
This is a linkpost for Apollo Research's new interpretability paper: "Interpretability in Parameter