Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
Paper
•
2601.10160
•
Published
•
1
Recommended Papers
Curated collection of research papers that I think are worth sharing or find particularly interesting.
-
-
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 507 -
MemOS: A Memory OS for AI System
Paper • 2507.03724 • Published • 158 -
Recursive Language Models
Paper • 2512.24601 • Published • 73 -
Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models
Paper • 2601.15220 • Published • 8