Lesser Wrong Feed

 One axis and two features, how I solved the first puzzle from BlueDot and how a classifier hid country on the food direction
 Fri, 03 Jul 2026 05:22:27 GMT
 Lydia Laurenson: "The Inside Story of Leverage Research"
 Thu, 02 Jul 2026 22:37:17 GMT
 When Role-playing, Do Models Believe What They Say?
 Thu, 02 Jul 2026 21:58:48 GMT
 The Case for AI Behavioral Science
 Thu, 02 Jul 2026 22:52:34 GMT
 You Should Choose How You React to Your Feelings
 Thu, 02 Jul 2026 19:58:35 GMT
 I can't think of great interventions for ensuring third-party model access.
 Thu, 02 Jul 2026 18:30:48 GMT
 AI Futurism Reading List
 Thu, 02 Jul 2026 18:15:38 GMT
 Research update: RL on Debate Games shows Proposal Accuracy uplift alongside Judge Hacking
 Thu, 02 Jul 2026 17:42:23 GMT
 Charter cities make sense in Europe
 Thu, 02 Jul 2026 17:24:25 GMT
 Conversation Among Cade Metz, Michael Vassar, Jessica Taylor, and Zack M. Davis
 Thu, 02 Jul 2026 17:11:37 GMT