00:00
2026-09-13
mindstudio.ai
artificial-intelligence
Recursive Self-Improvement Training: How NeoHorse-1-4B Learns From Itself
Token Rhythm's NeoHorse-1-4B, a 4 billion parameter model built on Qwen 3.5, was trained on live router decision logs rather than a static dataset, with a stronger teacher model correcting its attempt…