Anthropic Hardens Claude Against Distillation, Cutting Extraction 90-99%

Anthropic has deployed defenses that it says reduce model distillation attacks by 90 to 99 percent, treating the protection of its weights and behavior as core operational security.

Model theft has quietly become a first-order security problem, and Anthropic is responding accordingly. The company has hardened Claude against distillation attacks, cutting extraction by 90 to 99 percent, according to @marcopapa99. Distillation — training a cheaper model to mimic a frontier one by querying it at scale — is one of the main ways a competitor can capture much of a model's value without the cost of building it.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Proin pharetra nonummy pede. Mauris et orci. Aenean nec lorem. In porttitor. Donec laoreet nonummy augue. Suspendisse dui purus, scelerisque at, vulputate vitae, pretium mattis, nunc. Mauris eget neque at sem venenatis eleifend. Ut nonummy. Fusce aliquet pede non pede. Suspendisse dapibus lorem pellentesque magna integer malesuada.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief