Over the last few months, we’ve made significant progress in reducing the effectiveness of distillation attacks against Claude.
In this post, we explain how: https://t.co/uWiRSLBuOS
Anthropic describes progress in blunting distillationTraining a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.Full definition → attacks against Claude. If you build on or train against frontier model outputs, it signals tighter enforcement on using API outputs to train competing models.
Terms in this piece · Glossary
distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
