Lesser Wrong Feed

 Why Do Naive SFT Filters For Safety Properties Fail?
 Sun, 14 Jun 2026 19:45:10 GMT
 Why I think a global AI pause (almost) certainly won't happen
 Sun, 14 Jun 2026 19:20:23 GMT
 Can a stronger model fake being a weaker one? Mostly not
 Sun, 14 Jun 2026 17:30:48 GMT
 The Hidden Structures of Problems
 Sun, 14 Jun 2026 13:51:38 GMT
 Agent Identity Standardisation Efforts
 Sun, 14 Jun 2026 11:30:40 GMT
 Wikipedia's national flavors - French
 Sun, 14 Jun 2026 10:29:02 GMT
 Low-temperature bunk
 Sun, 14 Jun 2026 07:59:05 GMT
 I Bet Abliteration's Cost Was Sloppy Implementation. I Was Wrong
 Sun, 14 Jun 2026 09:44:45 GMT
 Don't just aim for Frontier Labs
 Sun, 14 Jun 2026 04:41:05 GMT
 Paying Kids To Do Schoolwork
 Sun, 14 Jun 2026 04:01:30 GMT