Safety probe error follows scaling laws in size and labels
Laws fitted on a family's smallest models predict the next model's error within 0.02 in 72% of cases.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
Laws fitted on a family's smallest models predict the next model's error within 0.02 in 72% of cases.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views