How I think about alignment and ethics as a cooperation protocol software
Published on October 1, 2025 9:09 PM GMTI think alignment by itself is complex phenomenon,…
Category: Opinion
Introducing the Mox Guest Program
Published on October 1, 2025 6:35 PM GMTTL;DR: Mox, a community space and incubator in…
Claude Sonnet 4.5 Is A Very Good Model
Published on October 1, 2025 6:00 PM GMTA few weeks ago, Anthropic announced Claude Opus…
My Brush with Superhuman Persuasion
Published on October 1, 2025 5:50 PM GMTA market experiment where I get blackmailed 1. Just…
AI and Cheap Weapons
Published on October 1, 2025 5:31 PM GMTThis article discusses the "Proliferation by Default" dynamic…
But what kind of stuff can you just do?
Published on October 1, 2025 4:58 PM GMTA phrase that has been popping up lately…
Lectures on statistical learning theory for alignment researchers
Published on October 1, 2025 8:36 AM GMTThis is a recorded series of lectures and…
Claude Sonnet 4.5: System Card and Alignment
Published on September 30, 2025 8:50 PM GMTClaude Sonnet 4.5 was released yesterday. Anthropic credibly…
Halfhaven virtual blogger camp
Published on September 30, 2025 8:22 PM GMTIf you are a blogger, or an aspiring…
The Basic Case For Doom
Published on September 30, 2025 4:04 PM GMTCrosspost of my blog article.A lot of the…