Anthropic Says New Defences Cut Claude Model Extraction By Up To 99%

Anthropic says it has made it substantially harder for rivals and other outside operators to extract the reasoning behind Claude’s answers for use in their own models. In research published on October 12, the company says new defences cut the number of reasoning tokens obtained by suspected model distillers on its platform by roughly 10 to 100 times. Put another way, Anthropic estimates a reduction of about 90% to 99% in the particular material it measured. That is a company-reported result from its own platform, not proof that every attempt to copy a model can be stopped.

First reported by TechBooky. This page is a short excerpt; the full text is theirs.