From raw model to assistantLesson 2 of 10Free preview
Learning from demonstrations
Show the model one good answer and raise its probability. Supervised fine-tuning lifts P(correct) from 26% to 82% in five updates.
From raw model to assistantLesson 2 of 10Free preview
Show the model one good answer and raise its probability. Supervised fine-tuning lifts P(correct) from 26% to 82% in five updates.