Lesser Wrong Feed

 Alignment vs. Safety, part 2: Alignment
 Wed, 08 Apr 2026 06:40:22 GMT
 The hard part isn't noticing when papers are bad, it's deciding what to do afterwards
 Wed, 08 Apr 2026 06:35:48 GMT
 Against Possible Worlds
 Wed, 08 Apr 2026 06:35:13 GMT
 AI as a Trojan horse race
 Wed, 08 Apr 2026 04:30:42 GMT
 We can prevent progress! Conceptual clarity, and inspiration from the FDA
 Wed, 08 Apr 2026 04:30:40 GMT
 Canberra: folk music
 Wed, 08 Apr 2026 04:30:38 GMT
 How I love running
 Wed, 08 Apr 2026 04:30:32 GMT
 An easy coordination problem?
 Wed, 08 Apr 2026 04:30:30 GMT
 How Does an Agent with Multiple Goals Choose a Target?
 Wed, 08 Apr 2026 04:21:23 GMT
 Is death and suffering axiomatically bad?
 Wed, 08 Apr 2026 03:47:11 GMT