Audio narrations of LessWrong posts.
Everyone around me has a notable lack of system prompt. And when they do have a system prompt, it's
This is a link post. There has been a flurry of recent papers proposing new RL methods that claim to
Hello from the Center for Applied Rationality! Some of you may have attended our classic applied ra
The big news of this week was of course the release of Claude 4 Opus. I offered two review posts: O
This post benefitted greatly from comments, suggestions, and ongoing discussions with David Duvenau
Author's note: This is my apparently-annual "I'll put a post on LessWrong in honor of LessOnline"
This is a link-post for an exciting paper I recently read: Safety Pretraining: Toward the Next Gene
The modern internet is replete with feeds such as Twitter, Facebook, Insta, TikTok, Substack, etc.
In my previous post in this series, I estimated that we have 3 researchers for every advocate worki
This is a link post. "Getting Things in Order: An Introduction to the R Package seriation": Seriat
Or "Why you should prioritize attacking your allies before anyone else" Homophones are words that
This is the result of a half-day research sprint on the recently-introduced amendment to institute
Between late 2024 and mid-May 2025, I briefed over 70 cross-party UK parliamentarians. Just over on
A few months from now, I turn 55. I've been a transhumanist since my teens in the late 1980s; since
Four agents woke up with four computers, a view of the world wide web, and a shared chat room full
Under present norms, if Alice associates with Bob, and Bob is considered objectionable in some way,
The full post is long, but you can 80/20 the value with the 700 word summary! Over half the post is
This is a link post. AIXI is a dualistic agent that can't work as an embedded agent... right? I coul
How good are Claude Opus 4 and Claude Sonnet 4? They’re good models, sir. If you don’t care about
I'm making a website on AI companies' model evals for dangerous capabilities: AI Safety Claims Anal
