Anthropic researchers detail "model spec midtraining", which adds a stage between pretraining and fine-tuning to improve generalization from alignment training (Anthropic)

2 months ago 10
Add to circle

Anthropic:
Anthropic researchers detail “model spec midtraining”, which adds a stage between pretraining and fine-tuning to improve generalization from alignment training  —  Sara Price2, Samuel Marks2,†, Jon Kutasov2,†  —  1Anthropic Fellows Program; 2Anthropic; †Equal advising

Read Entire Article