11:01
2026-10-01
dev.to
large-language-models
Darwin-180B-RSI: How VIDRAFT's Recursive Self-Improvement Model Topped 7 Hugging Face Leaderboards ā Without Legal Training Data
VIDRAFT released Darwin-180B-RSI, a 180-billion-parameter reasoning model trained with a weight-level Recursive Self-Improvement framework that updates model weights directly without human-annotated cā¦