Lesser Wrong Feed

 The AIXI perspective on AI Safety
 Tue, 24 Mar 2026 03:24:24 GMT
 Contra Dances Should Avoid Saturdays
 Tue, 24 Mar 2026 02:30:47 GMT
 Information Overdose
 Tue, 24 Mar 2026 04:45:50 GMT
 Every Major LLM is a 1-Box Smoking Thirder
 Tue, 24 Mar 2026 04:43:39 GMT
 A ToM-Inspired Agenda for AI Safety Research
 Tue, 24 Mar 2026 02:13:29 GMT
 Poking and Editing the Circuits
 Tue, 24 Mar 2026 01:28:45 GMT
 Adopt a debugger’s mindset to solve your recurring life problems
 Tue, 24 Mar 2026 00:22:49 GMT
 Experimental Evidence for Simulator Theory— Part 2: The Scalers Strike Back
 Mon, 23 Mar 2026 22:37:51 GMT
 Experimental Evidence for Simulator Theory— Part 1: Emergent Misalignment and Weird Generalizations
 Mon, 23 Mar 2026 22:37:00 GMT
 How Far Can Observation Take Us?
 Mon, 23 Mar 2026 21:56:47 GMT