Lesser Wrong Feed

 Is Eval Gaming Downstream of Verbalized Eval Awareness? Not when it's reflexive.
 Mon, 10 Aug 2026 08:24:50 GMT
 Is it ethical to work on general-purpose robots given the risk of totalitarianism?
 Mon, 10 Aug 2026 06:40:08 GMT
 How to be an AI safety research engineer
 Mon, 10 Aug 2026 05:32:00 GMT
 Hiring Vibe-wrangler Matchmaking Thread
 Mon, 10 Aug 2026 03:53:15 GMT
 How to get answers to questions that confuse you (maybe)
 Mon, 10 Aug 2026 01:35:13 GMT
 The Agentic Clusterfuck
 Mon, 10 Aug 2026 01:27:09 GMT
 Overthinking: Amplifying reasoning weights makes models reveal their secrets
 Sun, 09 Aug 2026 22:06:56 GMT
 AI-amplified democratic backsliding: an exploration
 Sun, 09 Aug 2026 22:10:11 GMT
 "Community Notes" resolution for vague predictions
 Sun, 09 Aug 2026 19:51:57 GMT
 Ten Thousand Cyber Labs for Training & Eval
 Sun, 09 Aug 2026 17:57:52 GMT