Lesser Wrong Feed

 Major survey on the HS/TS spectrum and gAyGP
 Mon, 27 Oct 2025 14:31:19 GMT
 Death of the Author
 Mon, 27 Oct 2025 12:35:32 GMT
 Exploring the multi-dimensional refusal subspace in reasoning models
 Mon, 27 Oct 2025 09:41:07 GMT
 AIs should also refuse to work on capabilities research
 Mon, 27 Oct 2025 08:42:35 GMT
 Uncommon Utilitarianism #3: Bounded Utility Functions
 Mon, 27 Oct 2025 05:06:25 GMT
 List of lists of project ideas in AI Safety
 Mon, 27 Oct 2025 08:26:25 GMT
 How valuable is money-in-market?
 Mon, 27 Oct 2025 00:47:29 GMT
 Credit goes to the presenter, not the inventor
 Sun, 26 Oct 2025 23:55:27 GMT
 On Fleshling Safety: A Debate by Klurl and Trapaucius.
 Sun, 26 Oct 2025 23:44:04 GMT
 Results of "Experiment on Bernoulli processes"
 Sun, 26 Oct 2025 21:47:44 GMT