Hacker News new | past | comments | ask | show | jobs | submit
ctxc | on: Amazon saves millions by replacing Sonnet 4.6 with Strands Decider
I'm sorry, can you restate - are you saying in house models are good enough even when there's no relevant training data?
asgraham | parent
They seem to be saying: route data that matches training data to the trained classifier, and route the rest to Jev.