Audio narrations of LessWrong posts.
Consider the following vignette: It is March 2028. With their new CoCo-Q neuralese reasoning model,
Currently, only 5 companies in the world have access to frontier AI training compute and are also p
You can find Part 1 here. This resumes the weekly, already in progress. The primary focus here is o
Highlights We stress-tested 16 leading models from multiple developers in hypothetical corporate e
The 1950s were crazy times. Human experimentation in the US was normalized in a way that would make
Audio note: this article contains 218 uses of latex notation, so the narration may be difficult to
It's currently possible to (mostly or fully) cheaply reproduce the performance of a model by traini
Audio note: this article contains 147 uses of latex notation, so the narration may be difficult to
Nate and Eliezer's forthcoming book has been getting a remarkably strong reception. I was under the
Background Concept: What World Does The Referent Live In? When we see some symbols representing som
First, how and why I made this game I spent several years working as the chief product officer of a
Audio note: this article contains 33 uses of latex notation, so the narration may be difficult to
Thanks to helpful commenters on the original post, especially Kaj Sotala. It's mostly thanks to Kaj
This is the abstract and introduction of our new paper: Emergent misalignment extends to reasoning
Ed and Anna are co-first authors on this work.TL;DR Recent work on Emergent Misalignment (EM)
Ed and Anna are co-first authors on this work.TL;DR Emergent Misalignment (EM) showed that fin
The RAISE Act has overwhelmingly passed the New York Assembly (95-1 among Democrats and 24-21 among
PDF version. berkeleygenomics.org. This is a short miscellaneous list of projects that I think wou
A while ago I saw a person in the comments on comments to Scott Alexander's blog arguing that a sup
I'd like to say thanks to Anna Magpie – who offers literature review as a service – for her help re
