Lesser Wrong Feed

 AI Safety at the Frontier: Paper Highlights of November 2025
 Tue, 02 Dec 2025 21:11:13 GMT
 Open Thread Winter 2025/26
 Tue, 02 Dec 2025 19:27:43 GMT
 Five ways AI can tell you're testing it
 Tue, 02 Dec 2025 17:25:48 GMT
 Why Moloch is actually the God of Evolutionary Prisoner’s Dilemmas
 Tue, 02 Dec 2025 16:54:24 GMT
 Reward Mismatches in RL Cause Emergent Misalignment
 Tue, 02 Dec 2025 16:31:17 GMT
 Sci.STEPS invites mentee applications
 Tue, 02 Dec 2025 13:33:56 GMT
 How Claude Opus 4.5 describes its experience of various concepts
 Tue, 02 Dec 2025 13:05:51 GMT
 Safety Cases Explained: How to Argue an AI is Safe
 Tue, 02 Dec 2025 11:03:00 GMT
 The Hidden Asymmetry in Personal Preparedness: Early Costs, Late Losses
 Tue, 02 Dec 2025 10:33:59 GMT
 Halfhaven Digest 6 + Retrospective
 Tue, 02 Dec 2025 05:27:03 GMT