Lesser Wrong Feed

 [Linkpost] Prefixing names with 'secure_' makes agents write more secure code
 Mon, 01 Jun 2026 21:20:39 GMT
 Can LLMs even teach? Exploring the Teacher Axis
 Mon, 01 Jun 2026 21:19:03 GMT
 Monitoring computer-use agents in OSWorld-control
 Mon, 01 Jun 2026 21:28:04 GMT
 Alignment to What?
 Mon, 01 Jun 2026 21:27:43 GMT
 Popperians, Bayesians and Ramseyians
 Mon, 01 Jun 2026 21:21:49 GMT
 Systems Dynamics Model for Pausing AI
 Mon, 01 Jun 2026 20:58:28 GMT
 Companions aren't Coaches: AIs' Effect on Social Skills
 Mon, 01 Jun 2026 19:30:25 GMT
 "Contagious Humming" to Silence a Room
 Mon, 01 Jun 2026 19:08:11 GMT
 Dissolving the Deep Learning Sample Efficiency Gap
 Mon, 01 Jun 2026 18:44:09 GMT
 We Need Breadth-First AI Safety Plans
 Mon, 01 Jun 2026 17:36:36 GMT